diff --git a/Dockerfile b/Dockerfile index 03840b97..e72d9b70 100644 --- a/Dockerfile +++ b/Dockerfile @@ -48,7 +48,7 @@ FROM nvidia/cuda:12.4.1-devel-ubuntu22.04 AS pytorch-install WORKDIR /usr/src/ # NOTE: When updating PyTorch version, beware to remove `pip install nvidia-nccl-cu12==2.22.3` below in the Dockerfile. Context: https://github.com/huggingface/text-generation-inference/pull/2099 -ARG PYTORCH_VERSION=2.6 +ARG PYTORCH_VERSION=2.7 ARG PYTHON_VERSION=3.11 # Keep in sync with `server/pyproject.toml diff --git a/flake.lock b/flake.lock index 6e187510..4540a736 100644 --- a/flake.lock +++ b/flake.lock @@ -978,15 +978,16 @@ "nixpkgs": "nixpkgs_6" }, "locked": { - "lastModified": 1743931123, - "narHash": "sha256-MDQrbJkweLYsMYh44Gx+c1gAZOCR1fmZF1lkavAHDto=", + "lastModified": 1746795305, + "narHash": "sha256-4fpUT4j4w0NDKF22KvG7iGmwQTBPM5SrPEqt+N3fqF0=", "owner": "huggingface", "repo": "text-generation-inference-nix", - "rev": "1ad3feaadfdedca90278ee7676bca15019519189", + "rev": "359cd25f31f0f2ad2cadfbf4e180780a7a06e3c5", "type": "github" }, "original": { "owner": "huggingface", + "ref": "torch-2.7", "repo": "text-generation-inference-nix", "type": "github" } diff --git a/flake.nix b/flake.nix index c733cdd2..e405b60d 100644 --- a/flake.nix +++ b/flake.nix @@ -5,7 +5,7 @@ inputs.nixpkgs.follows = "tgi-nix/nixpkgs"; }; nix-filter.url = "github:numtide/nix-filter"; - tgi-nix.url = "github:huggingface/text-generation-inference-nix"; + tgi-nix.url = "github:huggingface/text-generation-inference-nix/torch-2.7"; nixpkgs.follows = "tgi-nix/nixpkgs"; flake-utils.url = "github:numtide/flake-utils"; rust-overlay = { diff --git a/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgb_jpg.json b/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgb_jpg.json index ae67e006..41eb19fd 100644 --- a/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgb_jpg.json +++ b/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgb_jpg.json @@ -5,7 +5,7 @@ "index": 0, "logprobs": null, "message": { - "content": "Okay, let's analyze the image.\n\nThe image is a solid, bright white color. There is nothing else visible within it. \n\nIt's essentially a blank white canvas or a completely white square. \n\nIs there anything specific you'd like me to do with this image, such as describe it further or imagine what it might represent?", + "content": "Okay, let's analyze the image.\n\nThe image is a solid, bright white color. There is nothing else visible within it. \n\nIt's essentially a blank white square or rectangle.", "name": null, "role": "assistant", "tool_calls": null @@ -13,14 +13,14 @@ "usage": null } ], - "created": 1741965894, + "created": 1747062956, "id": "", "model": "google/gemma-3-4b-it", "object": "chat.completion", - "system_fingerprint": "3.2.1-dev0-native", + "system_fingerprint": "3.3.0-dev0-native", "usage": { - "completion_tokens": 74, + "completion_tokens": 42, "prompt_tokens": 277, - "total_tokens": 351 + "total_tokens": 319 } } diff --git a/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgb_png.json b/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgb_png.json index 786ced6c..1f3e2b91 100644 --- a/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgb_png.json +++ b/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgb_png.json @@ -1,11 +1,11 @@ { "choices": [ { - "finish_reason": "length", + "finish_reason": "stop", "index": 0, "logprobs": null, "message": { - "content": "Okay, let's analyze the image. \n\nThe image is entirely white, with a very subtle, faint outline of a stylized, cartoonish figure. It appears to be a simplified depiction of a person, likely a child, with a wide-eyed expression and a small, rounded body. \n\nIt's almost like a minimalist, iconic representation. \n\nDo you want me to try and describe it in more detail, or perhaps suggest what this image might represent (e.g", + "content": "Okay, let's analyze the image. \n\nThe image is a very plain, solid white square. That's it! \n\nIt's essentially a blank canvas. \n\nDo you want me to describe it in more detail, or are you interested in something else regarding this image?", "name": null, "role": "assistant", "tool_calls": null @@ -13,14 +13,14 @@ "usage": null } ], - "created": 1744396706, + "created": 1747062955, "id": "", "model": "google/gemma-3-4b-it", "object": "chat.completion", "system_fingerprint": "3.3.0-dev0-native", "usage": { - "completion_tokens": 100, + "completion_tokens": 62, "prompt_tokens": 277, - "total_tokens": 377 + "total_tokens": 339 } } diff --git a/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgba.json b/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgba.json index 571478ee..42a2be01 100644 --- a/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgba.json +++ b/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgba.json @@ -5,7 +5,7 @@ "index": 0, "logprobs": null, "message": { - "content": "Okay, let's analyze the image. \n\nThe transparent image reveals a stylized depiction of **a human head**. It's a minimalist, geometric representation, showing the basic shapes of the skull, eye sockets, and head outline. \n\nIf you'd like, you can give me more details about the image or ask me to focus on a specific aspect of it.", + "content": "Okay, let's analyze the image. \n\nThe transparent image reveals a stylized depiction of **a human head**. It's a minimalist, geometric representation, showing the basic shapes of the skull, eye sockets, and head outline. \n\nDo you want me to describe any specific element of the image in more detail?", "name": null, "role": "assistant", "tool_calls": null @@ -13,14 +13,14 @@ "usage": null } ], - "created": 1744396703, + "created": 1747062952, "id": "", "model": "google/gemma-3-4b-it", "object": "chat.completion", "system_fingerprint": "3.3.0-dev0-native", "usage": { - "completion_tokens": 78, + "completion_tokens": 67, "prompt_tokens": 277, - "total_tokens": 355 + "total_tokens": 344 } } diff --git a/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_cow.json b/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_cow.json index 9fb0c4c5..fbe95016 100644 --- a/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_cow.json +++ b/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_cow.json @@ -5,7 +5,7 @@ "index": 0, "logprobs": null, "message": { - "content": "Here's a description of what's shown in the image:\n\nThe image depicts a brown cow standing on a sandy beach. The beach has turquoise water and a distant island visible in the background. The sky is bright blue with some white clouds. \n\nIt's a quite a humorous and unusual scene – a cow enjoying a day at the beach!", + "content": "Here's a description of what's shown in the image:\n\nThe image depicts a brown cow standing on a sandy beach. The beach has turquoise water and a distant island visible in the background. The sky is bright blue with some white clouds. \n\nIt's a quite a humorous and unusual scene – a cow enjoying a beach day!", "name": null, "role": "assistant", "tool_calls": null @@ -13,14 +13,14 @@ "usage": null } ], - "created": 1744396699, + "created": 1747216083, "id": "", "model": "google/gemma-3-4b-it", "object": "chat.completion", "system_fingerprint": "3.3.0-dev0-native", "usage": { - "completion_tokens": 74, + "completion_tokens": 72, "prompt_tokens": 275, - "total_tokens": 349 + "total_tokens": 347 } } diff --git a/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_cow_dog.json b/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_cow_dog.json index 0ed2b1e1..40f317cc 100644 --- a/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_cow_dog.json +++ b/integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_cow_dog.json @@ -5,7 +5,7 @@ "index": 0, "logprobs": null, "message": { - "content": "That's a fantastic question! However, the image doesn't show a dog. It shows a **Brown Swiss cow** standing on a beach. \n\nBrown Swiss cows are known for their reddish-brown color and distinctive white markings. \n\nIf you'd like, you can send me another image and I’ll do my best to identify it!", + "content": "That's a fantastic question! However, the image doesn't show a dog. It shows a **Brown Swiss cow** standing on a beach. \n\nBrown Swiss cows are known for their beautiful reddish-brown coats and distinctive white markings. \n\nIf you'd like, you can send me another image, and I'll do my best to identify the animal in it!", "name": null, "role": "assistant", "tool_calls": null @@ -13,14 +13,14 @@ "usage": null } ], - "created": 1744396697, + "created": 1747216080, "id": "", "model": "google/gemma-3-4b-it", "object": "chat.completion", "system_fingerprint": "3.3.0-dev0-native", "usage": { - "completion_tokens": 75, + "completion_tokens": 80, "prompt_tokens": 279, - "total_tokens": 354 + "total_tokens": 359 } } diff --git a/integration-tests/models/__snapshots__/test_flash_pali_gemma2/test_flash_pali_gemma_image.json b/integration-tests/models/__snapshots__/test_flash_pali_gemma2/test_flash_pali_gemma_image.json index bc75bce4..90d787d4 100644 --- a/integration-tests/models/__snapshots__/test_flash_pali_gemma2/test_flash_pali_gemma_image.json +++ b/integration-tests/models/__snapshots__/test_flash_pali_gemma2/test_flash_pali_gemma_image.json @@ -8,126 +8,126 @@ "tokens": [ { "id": 108, - "logprob": -0.73046875, + "logprob": -0.48046875, "special": false, "text": "\n" }, { "id": 30234, - "logprob": -2.328125, + "logprob": -2.21875, "special": false, "text": "Brown" }, { "id": 108, - "logprob": -0.12060547, + "logprob": -0.119140625, "special": false, "text": "\n" }, { "id": 3726, - "logprob": -1.7734375, + "logprob": -1.703125, "special": false, "text": "Car" }, { "id": 108, - "logprob": -0.041503906, + "logprob": -0.0390625, "special": false, "text": "\n" }, { "id": 2915, - "logprob": -1.796875, + "logprob": -1.8203125, "special": false, "text": "Color" }, { "id": 108, - "logprob": -0.039794922, + "logprob": -0.035888672, "special": false, "text": "\n" }, { "id": 19178, - "logprob": -1.96875, + "logprob": -2.015625, "special": false, "text": "Cool" }, { "id": 108, - "logprob": -0.080566406, + "logprob": -0.08105469, "special": false, "text": "\n" }, { "id": 40544, - "logprob": -2.1875, + "logprob": -2.09375, "special": false, "text": "Decor" }, { "id": 108, - "logprob": -0.033935547, + "logprob": -0.038330078, "special": false, "text": "\n" }, { - "id": 13936, + "id": 108, + "logprob": -1.515625, + "special": false, + "text": "\n" + }, + { + "id": 108, + "logprob": -1.8671875, + "special": false, + "text": "\n" + }, + { + "id": 108, "logprob": -1.6328125, "special": false, - "text": "Green" + "text": "\n" }, { "id": 108, - "logprob": -0.16210938, + "logprob": -1.265625, "special": false, "text": "\n" }, - { - "id": 955, - "logprob": -2.015625, - "special": false, - "text": "..." - }, { "id": 108, - "logprob": -0.14746094, + "logprob": -1.0078125, "special": false, "text": "\n" }, - { - "id": 955, - "logprob": -0.73828125, - "special": false, - "text": "..." - }, { "id": 108, - "logprob": -0.051513672, + "logprob": -1.03125, "special": false, "text": "\n" }, { - "id": 955, - "logprob": -0.34765625, + "id": 235336, + "logprob": -1.2109375, "special": false, - "text": "..." + "text": "?" }, { "id": 108, - "logprob": -0.020141602, + "logprob": -0.29101562, "special": false, "text": "\n" }, { - "id": 955, - "logprob": -0.11767578, + "id": 235336, + "logprob": -0.08935547, "special": false, - "text": "..." + "text": "?" } ], "top_tokens": null }, - "generated_text": "\nBrown\nCar\nColor\nCool\nDecor\nGreen\n...\n...\n...\n..." + "generated_text": "\nBrown\nCar\nColor\nCool\nDecor\n\n\n\n\n\n\n?\n?" } diff --git a/integration-tests/models/__snapshots__/test_idefics/test_idefics_two_images.json b/integration-tests/models/__snapshots__/test_idefics/test_idefics_two_images.json index a4727707..46e67856 100644 --- a/integration-tests/models/__snapshots__/test_idefics/test_idefics_two_images.json +++ b/integration-tests/models/__snapshots__/test_idefics/test_idefics_two_images.json @@ -2,84 +2,90 @@ "details": { "best_of_sequences": null, "finish_reason": "eos_token", - "generated_tokens": 12, + "generated_tokens": 13, "prefill": [], "seed": null, "tokens": [ { "id": 450, - "logprob": -0.26342773, + "logprob": -0.2602539, "special": false, "text": " The" }, { "id": 21282, - "logprob": -0.01838684, + "logprob": -0.018463135, "special": false, "text": " cow" }, { "id": 322, - "logprob": -0.18041992, + "logprob": -0.1829834, "special": false, "text": " and" }, { "id": 521, - "logprob": -0.62841797, + "logprob": -0.62109375, "special": false, "text": " ch" }, { "id": 21475, - "logprob": -0.0037956238, + "logprob": -0.0037403107, "special": false, "text": "icken" }, { "id": 526, - "logprob": -0.018737793, + "logprob": -0.018920898, "special": false, "text": " are" }, + { + "id": 13407, + "logprob": -1.0732422, + "special": false, + "text": " standing" + }, { "id": 373, - "logprob": -1.0820312, + "logprob": -0.5292969, "special": false, "text": " on" }, { "id": 263, - "logprob": -0.5083008, + "logprob": -0.47070312, "special": false, "text": " a" }, { "id": 25695, - "logprob": -0.07128906, + "logprob": -0.25708008, "special": false, "text": " beach" }, { "id": 29889, - "logprob": -0.12573242, + "logprob": -0.17578125, "special": false, "text": "." }, { "id": 32002, - "logprob": -0.0029792786, + "logprob": -0.0023422241, "special": true, "text": "" }, { "id": 2, - "logprob": -0.00024962425, + "logprob": -0.00030851364, "special": true, "text": "" } ], "top_tokens": null }, - "generated_text": " The cow and chicken are on a beach." + "generated_text": " The cow and chicken are standing on a beach." } diff --git a/integration-tests/models/__snapshots__/test_mamba/test_mamba_all_params.json b/integration-tests/models/__snapshots__/test_mamba/test_mamba_all_params.json index ef88926c..1c18cae9 100644 --- a/integration-tests/models/__snapshots__/test_mamba/test_mamba_all_params.json +++ b/integration-tests/models/__snapshots__/test_mamba/test_mamba_all_params.json @@ -64,7 +64,7 @@ }, { "id": 329, - "logprob": -2.171875, + "logprob": -2.296875, "special": false, "text": " A" }, @@ -81,19 +81,19 @@ "text": " of" }, { - "id": 1027, - "logprob": -1.5546875, + "id": 253, + "logprob": -0.86328125, "special": false, - "text": " different" + "text": " the" }, { "id": 3295, - "logprob": -0.97265625, + "logprob": -0.55078125, "special": false, "text": " color" } ], "top_tokens": null }, - "generated_text": "blue, red, yellow, \nand blue colors. A number of different color" + "generated_text": "blue, red, yellow, \nand blue colors. A number of the color" } diff --git a/integration-tests/models/__snapshots__/test_mllama/test_mllama_load.json b/integration-tests/models/__snapshots__/test_mllama/test_mllama_load.json index 9d4c98ef..37c8ef8e 100644 --- a/integration-tests/models/__snapshots__/test_mllama/test_mllama_load.json +++ b/integration-tests/models/__snapshots__/test_mllama/test_mllama_load.json @@ -14,9 +14,9 @@ "usage": null } ], - "created": 1746054921, + "created": 1747230173, "id": "", - "model": "meta-llama/Llama-3.2-11B-Vision-Instruct", + "model": "unsloth/Llama-3.2-11B-Vision-Instruct", "object": "chat.completion", "system_fingerprint": "3.3.0-dev0-native", "usage": { @@ -40,9 +40,9 @@ "usage": null } ], - "created": 1746054921, + "created": 1747230173, "id": "", - "model": "meta-llama/Llama-3.2-11B-Vision-Instruct", + "model": "unsloth/Llama-3.2-11B-Vision-Instruct", "object": "chat.completion", "system_fingerprint": "3.3.0-dev0-native", "usage": { diff --git a/integration-tests/models/__snapshots__/test_mllama/test_mllama_simpl.json b/integration-tests/models/__snapshots__/test_mllama/test_mllama_simpl.json index d1049ead..75dc0ddf 100644 --- a/integration-tests/models/__snapshots__/test_mllama/test_mllama_simpl.json +++ b/integration-tests/models/__snapshots__/test_mllama/test_mllama_simpl.json @@ -5,7 +5,7 @@ "index": 0, "logprobs": null, "message": { - "content": "A chicken stands on a pile of money, looking", + "content": "A chicken sits on a pile of money, looking", "name": null, "role": "assistant", "tool_calls": null @@ -13,9 +13,9 @@ "usage": null } ], - "created": 1746054919, + "created": 1747230171, "id": "", - "model": "meta-llama/Llama-3.2-11B-Vision-Instruct", + "model": "unsloth/Llama-3.2-11B-Vision-Instruct", "object": "chat.completion", "system_fingerprint": "3.3.0-dev0-native", "usage": { diff --git a/integration-tests/models/__snapshots__/test_smolvlm/test_flash_smolvlm_next_simple_url.json b/integration-tests/models/__snapshots__/test_smolvlm/test_flash_smolvlm_next_simple_url.json index 17a69d0d..5a30fd80 100644 --- a/integration-tests/models/__snapshots__/test_smolvlm/test_flash_smolvlm_next_simple_url.json +++ b/integration-tests/models/__snapshots__/test_smolvlm/test_flash_smolvlm_next_simple_url.json @@ -8,49 +8,49 @@ "tokens": [ { "id": 330, - "logprob": -0.118652344, + "logprob": -0.107421875, "special": false, "text": " A" }, { "id": 11426, - "logprob": -0.28320312, + "logprob": -0.30078125, "special": false, "text": " bee" }, { "id": 335, - "logprob": -0.95703125, + "logprob": -0.9609375, "special": false, "text": " on" }, { "id": 253, - "logprob": -0.06982422, + "logprob": -0.0703125, "special": false, "text": " a" }, { "id": 11986, - "logprob": -0.49414062, + "logprob": -0.5, "special": false, "text": " pink" }, { "id": 8525, - "logprob": -0.07763672, + "logprob": -0.09716797, "special": false, "text": " flower" }, { "id": 30, - "logprob": -1.0703125, + "logprob": -1.078125, "special": false, "text": "." }, { "id": 49154, - "logprob": -0.092285156, + "logprob": -0.110839844, "special": true, "text": "" } diff --git a/integration-tests/models/test_flash_gemma3.py b/integration-tests/models/test_flash_gemma3.py index 5064f34d..cd9d98ea 100644 --- a/integration-tests/models/test_flash_gemma3.py +++ b/integration-tests/models/test_flash_gemma3.py @@ -53,9 +53,9 @@ async def test_flash_gemma3_image_cow_dog(flash_gemma3, response_snapshot): assert ( response.choices[0].message.content - == "That's a fantastic question! However, the image doesn't show a dog. It shows a **Brown Swiss cow** standing on a beach. \n\nBrown Swiss cows are known for their reddish-brown color and distinctive white markings. \n\nIf you'd like, you can send me another image and I’ll do my best to identify it!" + == "That's a fantastic question! However, the image doesn't show a dog. It shows a **Brown Swiss cow** standing on a beach. \n\nBrown Swiss cows are known for their beautiful reddish-brown coats and distinctive white markings. \n\nIf you'd like, you can send me another image, and I'll do my best to identify the animal in it!" ) - assert response.usage["completion_tokens"] == 75 + assert response.usage["completion_tokens"] == 80 assert response == response_snapshot @@ -76,9 +76,9 @@ async def test_flash_gemma3_image_cow(flash_gemma3, response_snapshot): ) assert ( response.choices[0].message.content - == "Here's a description of what's shown in the image:\n\nThe image depicts a brown cow standing on a sandy beach. The beach has turquoise water and a distant island visible in the background. The sky is bright blue with some white clouds. \n\nIt's a quite a humorous and unusual scene – a cow enjoying a day at the beach!" + == "Here's a description of what's shown in the image:\n\nThe image depicts a brown cow standing on a sandy beach. The beach has turquoise water and a distant island visible in the background. The sky is bright blue with some white clouds. \n\nIt's a quite a humorous and unusual scene – a cow enjoying a beach day!" ) - assert response.usage["completion_tokens"] == 74 + assert response.usage["completion_tokens"] == 72 assert response == response_snapshot diff --git a/integration-tests/models/test_flash_pali_gemma2.py b/integration-tests/models/test_flash_pali_gemma2.py index 23705385..bef9628d 100644 --- a/integration-tests/models/test_flash_pali_gemma2.py +++ b/integration-tests/models/test_flash_pali_gemma2.py @@ -22,8 +22,7 @@ async def test_flash_pali_gemma_image(flash_pali_gemma, response_snapshot): max_new_tokens=20, ) assert ( - response.generated_text - == "\nBrown\nCar\nColor\nCool\nDecor\nGreen\n...\n...\n...\n..." + response.generated_text == "\nBrown\nCar\nColor\nCool\nDecor\n\n\n\n\n\n\n?\n?" ) assert response == response_snapshot diff --git a/integration-tests/models/test_idefics.py b/integration-tests/models/test_idefics.py index e5d08bb7..848a6674 100644 --- a/integration-tests/models/test_idefics.py +++ b/integration-tests/models/test_idefics.py @@ -39,7 +39,7 @@ async def test_idefics_two_images(idefics, response_snapshot, chicken, cow_beach max_new_tokens=20, ) assert ( - response.generated_text == " The cow and chicken are on a beach." + response.generated_text == " The cow and chicken are standing on a beach." ), f"{repr(response.generated_text)}" assert response == response_snapshot diff --git a/integration-tests/models/test_mamba.py b/integration-tests/models/test_mamba.py index baa19643..ec0f90a1 100644 --- a/integration-tests/models/test_mamba.py +++ b/integration-tests/models/test_mamba.py @@ -47,7 +47,7 @@ async def test_mamba_all_params(fused_kernel_mamba, response_snapshot): assert response.details.generated_tokens == 10 assert ( response.generated_text - == "blue, red, yellow, \nand blue colors. A number of different color" + == "blue, red, yellow, \nand blue colors. A number of the color" ) assert response == response_snapshot diff --git a/integration-tests/models/test_mllama.py b/integration-tests/models/test_mllama.py index 95ec1d99..fd58e4bf 100644 --- a/integration-tests/models/test_mllama.py +++ b/integration-tests/models/test_mllama.py @@ -5,7 +5,7 @@ import asyncio @pytest.fixture(scope="module") def mllama_handle(launcher): with launcher( - "meta-llama/Llama-3.2-11B-Vision-Instruct", + "unsloth/Llama-3.2-11B-Vision-Instruct", num_shard=2, ) as handle: yield handle @@ -48,7 +48,7 @@ async def test_mllama_simpl(mllama, response_snapshot): } assert ( response.choices[0].message.content - == "A chicken stands on a pile of money, looking" + == "A chicken sits on a pile of money, looking" ) assert response == response_snapshot diff --git a/server/Makefile b/server/Makefile index cf6c7370..f4855392 100644 --- a/server/Makefile +++ b/server/Makefile @@ -38,7 +38,7 @@ install: install-cuda echo "Installed server" install-cuda: install-server install-flash-attention-v2-cuda install-flash-attention - uv sync --inexact --extra attention --extra bnb --extra marlin --extra moe --active + uv sync --inexact --extra attention --extra bnb --active uv pip install nvidia-nccl-cu12==2.22.3 kernels download . @@ -46,6 +46,6 @@ install-rocm: install-server install-flash-attention-v2-rocm install-vllm-rocm export-requirements: uv pip compile pyproject.toml --extra gen -o requirements_gen.txt --python-version 3.11 - uv pip compile pyproject.toml --extra attention --extra bnb --extra accelerate --extra compressed-tensors --extra marlin --extra moe --extra quantize --extra peft --extra outlines -o requirements_cuda.txt --python-version 3.11 + uv pip compile pyproject.toml --extra bnb --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_cuda.txt --python-version 3.11 uv pip compile pyproject.toml --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_intel.txt --python-version 3.11 uv pip compile pyproject.toml --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_rocm.txt --python-version 3.11 diff --git a/server/kernels.lock b/server/kernels.lock index 9e11de68..1bce05c6 100644 --- a/server/kernels.lock +++ b/server/kernels.lock @@ -1,270 +1,410 @@ [ { "repo_id": "kernels-community/paged-attention", - "sha": "331b7e63a6b592799c8bc992f681bb1ee2c865a2", + "sha": "1e0a9708f0fe47009a3d292226c5492474353258", "variants": { "torch25-cxx11-cu118-x86_64-linux": { - "hash": "sha256-8e0aa39abab82f1d21b661d35e0470a24c3ebbdda38532ded805c18037a1ad1e", + "hash": "sha256-99710450ce815fdd0eeab3862ed0940c37a236c4f6cd49399e0112d66c9e40cb", "hash_type": "git_lfs_concat" }, "torch25-cxx11-cu121-x86_64-linux": { - "hash": "sha256-b0c3aef6c4c9aac627975cb1a2bfc46a70390763c8165575b89d1651d007c38a", + "hash": "sha256-bf136ffb4732e141e05738606a014fde18d3aa6d4345d6223858327c00eef2d1", "hash_type": "git_lfs_concat" }, "torch25-cxx11-cu124-x86_64-linux": { - "hash": "sha256-960fbc8998439d779adb47fb2a37cce68c7dc075d8a49893bd487be9ca2d1389", + "hash": "sha256-5ff343fc4feadf36ea38032d2a014a1cd6008fe22dea26191cd397745dbaf8ae", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu118-x86_64-linux": { - "hash": "sha256-9d6d60c411c55aa2f9d7c681c2be96f4262d56c96f592f3d4fb35ce4f4f1e18e", + "hash": "sha256-5db4fd37dcc6ec49ea71eba49415758b98fc21699155632902c76a545b36c47a", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu121-x86_64-linux": { - "hash": "sha256-98c0a305b2cc9b7be757fab923d9aa406c686dcd0460e462926f87d051ef3d19", + "hash": "sha256-995ff1a0cfe569639bc1644b5d6d823ea47ad0da33fe1cf398370ee70a203eb3", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu124-x86_64-linux": { - "hash": "sha256-71e586416213c96ffbdeae0d077ba97bfde5b00005f2746d4cba2320cb53bf87", + "hash": "sha256-1a00b021ea1273acb003ebd459699287ebf3d03f949befa31ae91899fa90b9e8", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu118-x86_64-linux": { - "hash": "sha256-2f559312c54d558b33a4082ffc3fcf923f51da40ced19bfc8920e998ba2b71bf", + "hash": "sha256-91e57835ae0f6e2df38c65c9e2eb47d33b609c7c117f6a86898740ad17653dba", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu124-x86_64-linux": { - "hash": "sha256-6033b41a0f8a9509887c6171f0b42d9aa738490903b3fd5ea2c52703c5fb8fc3", + "hash": "sha256-5435890298a7eca613c805c8aee08b5a4405a1a7ad38ad3bc43bba14b26683ae", + "hash_type": "git_lfs_concat" + }, + "torch26-cxx11-cu126-aarch64-linux": { + "hash": "sha256-b3dffef571f4f813b727ce3b2fcb7b43ee9d2e793b594e6ccf3a694bac87280a", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu126-x86_64-linux": { - "hash": "sha256-3139f66a53f2bf0c314b4d309893095746bdc9c3914c904fc31adfdf553ed219", + "hash": "sha256-7ce5d58943f52959cc9643477e4dc211c7592628968cc53714e307092c95a769", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu118-x86_64-linux": { - "hash": "sha256-2173d77e384d8e2881fc38603992c09e8be7bcd9da4cafdd4f2a5ce0ce22caf4", + "hash": "sha256-c74c251ba84cf6ea4c0402ed6dec7dca92f46b101f299a0abb1bcab5c83d2165", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu124-x86_64-linux": { - "hash": "sha256-7b1aaef81e01ecce83e03c50872910680ff2953f7c6ffd3ff15e8d9497ca9239", + "hash": "sha256-44661e14516679bfa1788a4919c01014e9cd2402ad6231947bf7a6ca55002ecd", + "hash_type": "git_lfs_concat" + }, + "torch26-cxx98-cu126-aarch64-linux": { + "hash": "sha256-e28ca88f80f95eede03eae610c08f83caabe579e15d110d9e070e46b6435770f", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu126-x86_64-linux": { - "hash": "sha256-818b160a88b12b8e871099e40f76aa436ee828e2e060ecc35502dbe34a6ebd3b", + "hash": "sha256-05eb63f56b6b665d0e25919a8f429c8c3b2e0e3fc55725885d0e68e9011ca283", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu118-x86_64-linux": { + "hash": "sha256-ef0c14844fd8df0ce765b85497c90ce1091b4a780642d86bf206799ba9d3c94a", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu126-aarch64-linux": { + "hash": "sha256-ab151aea475c6880ed15e8f9232bf8720f7f0f2b96acdac65a5bcb7e5ab727b1", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu126-x86_64-linux": { + "hash": "sha256-08345dd704dcea727b9c2c109664f1602f97908fed84522edb817d95eb859f74", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu128-aarch64-linux": { + "hash": "sha256-c2419e4057e26bd90360dacd30f1b51eea1fde2efed9bd4c7db034ffc2962a5a", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu128-x86_64-linux": { + "hash": "sha256-a85fa6b43d438380c9d064769d8dd509ebf5206327a326082c0c249c0704ca46", "hash_type": "git_lfs_concat" } } }, { "repo_id": "kernels-community/moe", - "sha": "605a216f507b9a97b543140dee8937a4622069a8", + "sha": "e3efab933893cde20c5417ba185fa3b7cc811b24", "variants": { "torch25-cxx11-cu118-x86_64-linux": { - "hash": "sha256-855d92f02be3bfba0758161fa1266159d76c172e7c5d43d30816d22cfba76074", + "hash": "sha256-719817bc2320f52d510e4a62bceef41a0ba8c58ea0e67d844db4225add3c5783", "hash_type": "git_lfs_concat" }, "torch25-cxx11-cu121-x86_64-linux": { - "hash": "sha256-e6e780230477bbbc26fc40cc7fcff50298155998af4fc77a026c9f815ec984b1", + "hash": "sha256-1b5973b5d9376e377ff223aed71936cc25f19367c8db7fcd9aa70960c15de290", "hash_type": "git_lfs_concat" }, "torch25-cxx11-cu124-x86_64-linux": { - "hash": "sha256-52c1fb337033c4d1d7a279c5cb28aebbc7389976f21dc5803aeb16b2f7aeb94c", + "hash": "sha256-69e1e5603c01227c3e2cbd67c09dd39fa7c0d4ecf3f736a2eb07227f6bb8935b", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu118-x86_64-linux": { - "hash": "sha256-1fb654e8d02dda2a2382d1fb3a3ca9738d292eea674b30b80030cdcdfb6a0035", + "hash": "sha256-91626ab4046b04e1a0967cc5c8a60a248e611b413e1cace3e4bdb0fc3a68a0e4", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu121-x86_64-linux": { - "hash": "sha256-0cf235f1de85d4ce7490c79aa64220f608f886f313b676d91c331a6a2fd67bbb", + "hash": "sha256-84dd628239aa3043bc048c51f513faf55042ccc3d372002bbc231b0aa6d6689f", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu124-x86_64-linux": { - "hash": "sha256-3def11fee9bf1ea9b1579206fd5f5ecbcaad47ac478e2c3aa7b2c9c7fd5db934", + "hash": "sha256-ffb9743f69aae59fba1cfed1fc9e2e0f90a9000121c2db5880f0e055a714931a", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu118-x86_64-linux": { - "hash": "sha256-3a49ee03f675190a79c7c74a45cc403d491eceb63a943f47d52064a11ca6ef6f", + "hash": "sha256-30560d5c091a9be1914fc8bf42d86767cfb07f1b7335f1ee88797e42f31e7856", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu124-x86_64-linux": { - "hash": "sha256-dbf20cb11db7d53e11147ab13641eefaa235f9ac2fde1beaf8f56f850c11bd54", + "hash": "sha256-6e2afd532fdc9cee8f532097a80e4c2139f47df8005c43c5cdac42204d6217e1", + "hash_type": "git_lfs_concat" + }, + "torch26-cxx11-cu126-aarch64-linux": { + "hash": "sha256-93d46cc7701358cd5a4e5ae3fafde8120fdb765149b9a9224f52a802b7d48cf1", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu126-x86_64-linux": { - "hash": "sha256-8a07232ab316e8eab74747662cb7b86aac03f44ff158f275768fd59390df2525", + "hash": "sha256-e57c961ea9c1a411c5b348986e359b1e6f1102fa09cfaa82d20f96d09528098a", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu118-x86_64-linux": { - "hash": "sha256-cdd46301af997eeace5e016d8590969981b3a3f8647828d04baa5fa10c696746", + "hash": "sha256-946b982082c008220a667f44e4308c17933e0d4785cad72ececa35273275f09c", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu124-x86_64-linux": { - "hash": "sha256-c865188e9d2c17f3358f3d343fb40340232457572744bf85efd6b20af545d5f3", + "hash": "sha256-227be46b6cc468fadc237bb616d14e4747ad122bc0a2cd5bbef1a2b89a63d5bf", + "hash_type": "git_lfs_concat" + }, + "torch26-cxx98-cu126-aarch64-linux": { + "hash": "sha256-d0dc0c8f34608f7c735e804c606dff029708349e68d5b9d9df7541b2498c1e8e", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu126-x86_64-linux": { - "hash": "sha256-2a8b09f3272ea80491e78a39ff886680471d99f7ba571581809adfe918013898", + "hash": "sha256-91b3df206bd4418e42d08608fdf652d65612342efc8f67958a66d68038179567", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu118-x86_64-linux": { + "hash": "sha256-4b0f4536cd8f24ef00f06e00dfa0123c03dada7de3394a6274ec5cfa3bbf31f6", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu126-aarch64-linux": { + "hash": "sha256-4c8468437ac977116f46be9a6871b0887f762ba44d3aea3c3ce2eb41637fb626", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu126-x86_64-linux": { + "hash": "sha256-9a0d84b8636a897e4a5abd243f48a71d7d470c2f8e28df6a6874a9d981105c0f", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu128-aarch64-linux": { + "hash": "sha256-11e6c4ce82a25d17664b4100af419f974fc312ac283195129c91519dac4d5812", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu128-x86_64-linux": { + "hash": "sha256-c49a6eda12752adf78690a5e985a55d3b85d6724be5d18db51cd03d5fc75cc9b", "hash_type": "git_lfs_concat" } } }, { "repo_id": "kernels-community/quantization", - "sha": "95272c71ca71b1ddbacb0105dab54e5d5240bd5c", + "sha": "6470f9b005797e00279eb9103463dfe0f8b7da00", "variants": { "torch25-cxx11-cu118-x86_64-linux": { - "hash": "sha256-2d0a274cf0117bf7880d6040adafa1b70fe8bff3a00ef2834ed5435a6b525a49", + "hash": "sha256-f52c9b1a7cd98fb389c6d2a0b22a293cb36eb96af3a624f5aec761735861c96d", "hash_type": "git_lfs_concat" }, "torch25-cxx11-cu121-x86_64-linux": { - "hash": "sha256-116458beac63ea5eeb1e7fba7edc68d160cd8ac28f55b926d79035551aac7d5f", + "hash": "sha256-e5f0da343363a562ce52f147a9534cd54a3efa90e70671f606cc2516f02a3876", "hash_type": "git_lfs_concat" }, "torch25-cxx11-cu124-x86_64-linux": { - "hash": "sha256-cace644c6fb04470384796c18987135cb051dfb90a14e902c51a3786fc07c599", + "hash": "sha256-caad9300c155faf79c26426f10951ba75f931a05e741a5b39a24b064daabc040", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu118-x86_64-linux": { - "hash": "sha256-104c6961cd3e1a74efdf14ea2172acc6647846852fccafe3698a27a6cf37941d", + "hash": "sha256-4fc87893de14a29ba4b55f5026ea05ec5901c0b52abd5ebae681ea0b791e858c", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu121-x86_64-linux": { - "hash": "sha256-cdc95b41aa91a803f11f8cd53001895c2b69550b5af2fb278d6f124381229d0b", + "hash": "sha256-72c975ea63fc524a38fcee5b2dbdb566eff0a0ea546ee5756441d04908e4e896", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu124-x86_64-linux": { - "hash": "sha256-d5388469cb6074f196f20b1e1e4805bb3c967a8147b31ca2c0461aa87b50604e", + "hash": "sha256-28c5510e3b07eae2b3846b880f6111da65df024e1f24f81077d187a97c015364", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu118-x86_64-linux": { - "hash": "sha256-70c4bb3792c4c3207d4963173d8d0ef3b2bda677151aef140662dd87bfa1b69f", + "hash": "sha256-8444cf77686578a6b0f7e2fd29bf2783ba120ebf7df41573f61d2521fd0acc10", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu124-x86_64-linux": { - "hash": "sha256-bcacbb2232f49345f27e07fa821b48a7e3df643c01af37281fcafc74c471f682", + "hash": "sha256-6ea8e00625b5fe799fbe407e7de0fc08228cac26f9bbed2d70a6500026fe3bab", + "hash_type": "git_lfs_concat" + }, + "torch26-cxx11-cu126-aarch64-linux": { + "hash": "sha256-0b8b8afbdaf9aa533895cb9e884e3ad3e9a34d483f05a1bbde1b8902f9dbeb0f", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu126-x86_64-linux": { - "hash": "sha256-344d20964f7eb133e5ec6fda976fa5ee62807b739a4361f236aca5ae53beb9ac", + "hash": "sha256-e115e855d7ca4b97787f04c88e128432256c6b43d4823fb8889ab9985dc4cf36", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu118-x86_64-linux": { - "hash": "sha256-dfaec226550254fbce1a5c7e2f547e85700958a1a4087e1c873d22e6f71a5ceb", + "hash": "sha256-509f08c48a05584cc85c058607277fcbe3193e6cc61846dd2416d39e27c1d68e", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu124-x86_64-linux": { - "hash": "sha256-0abe6460d0a2202b0086e3663092595e5b93b9a9cbb85c10034180cc9bfebc6e", + "hash": "sha256-a10236bffd435296c736ae2762ab0836da2421297e46b377368a17b39d70c27b", + "hash_type": "git_lfs_concat" + }, + "torch26-cxx98-cu126-aarch64-linux": { + "hash": "sha256-ca2cb56f3eea4c399a61e21ba9b577d718b250aa60a13f42f01019ddd5cd8b0c", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu126-x86_64-linux": { - "hash": "sha256-68e156f94c3c0c9523773b62eaeced93766e0d9ee67d8191fb9570fb5af30d5b", + "hash": "sha256-8fcd62d8243a30b63a03751cc0c15d24f6e00e43eae79f7281627f24e078bf9a", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu118-x86_64-linux": { + "hash": "sha256-60f5807ee3da937c57c1b6080c30632305aa4875ed5a52bf4e81968770b61b13", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu126-aarch64-linux": { + "hash": "sha256-64298b1713dc1d950915dc6569a06e2f541de3ed80aa5b32084246c1fdc7a958", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu126-x86_64-linux": { + "hash": "sha256-d9e219890dc28e8582ef21d6f81f2ebc361de218a86b742be63bc4714f102e5e", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu128-aarch64-linux": { + "hash": "sha256-d72549f51aefcf020bc74262bbbccb78094638c5ab9adc8667873d247c1cce86", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu128-x86_64-linux": { + "hash": "sha256-d31ac5f87d7c7f62c63c72946479193aed467c9417c0acead5137e0e1fa968f8", "hash_type": "git_lfs_concat" } } }, { "repo_id": "kernels-community/quantization-eetq", - "sha": "a80ce846d6270ddddeee109523ed947f594f246b", + "sha": "1aa83b1261b0c4cad890184a4d689e6330a110b5", "variants": { "torch25-cxx11-cu118-x86_64-linux": { - "hash": "sha256-e06beb00799b1e656583eb0496f09fc0bf1b26f75e9864a2fe19ebd5b62c3671", + "hash": "sha256-de257728ec38f48220d6c90b2fd960fed1f4c963e7cd6c204abfcf8607aedc20", "hash_type": "git_lfs_concat" }, "torch25-cxx11-cu121-x86_64-linux": { - "hash": "sha256-c128d3ef6558cfedf045c4a713891792708851b7f6f027de835d9083cb3b297d", + "hash": "sha256-9027918cf6e52591f97b2c621355e12d9adf0dfe833a763219813bfecd1ad1a3", "hash_type": "git_lfs_concat" }, "torch25-cxx11-cu124-x86_64-linux": { - "hash": "sha256-c7e2e14fc114788634b34a4f670f7bf4d27321e5ed40ff446f5a25eef70222c7", + "hash": "sha256-15cd0a56311897b27ee50617491cf69e698053a9f9af7bd37937cbca8da9db13", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu118-x86_64-linux": { - "hash": "sha256-58dad53cfbf1315af464f9d8ba7be9012089c839d4f06a8d2cf8ce0deaf5949a", + "hash": "sha256-ca35ccbb193c795587f4a0ea072fda6f0a0ac7f745f7a68e35c35012098f0a57", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu121-x86_64-linux": { - "hash": "sha256-6519af49c0f689744a7b49497ad2bea1524b69e4095446087d7ab622b898aa30", + "hash": "sha256-e7b12bd79163ee0f520b4a399f69c29e4a692667edf27f7d100f053434d8840c", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu124-x86_64-linux": { - "hash": "sha256-94e0731b58a9ba0e5e2f37b100c8d987c80b5d349008ef625917d020b6c52d25", + "hash": "sha256-f08e850e856faa42c992188affa898a9b5a7be9d64980c4193871b0ad999da78", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu118-x86_64-linux": { - "hash": "sha256-e5b04475538f49d7b4ffded080e4c9c86a658abc12667e3838ebcc410ab1eef4", + "hash": "sha256-9596f1c7cdbc7adf75898d18f370dc33ce0dfab2559301244411f5f4c4e581d4", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu124-x86_64-linux": { - "hash": "sha256-783c02db737a6ec9958b3090f164b87888d3b26e30a4fb6e1cd0c1a635753fab", + "hash": "sha256-90002710f9e59d12bff260ce288c2b2b954f988f94ef920c8384c97946b7782b", + "hash_type": "git_lfs_concat" + }, + "torch26-cxx11-cu126-aarch64-linux": { + "hash": "sha256-d230dd53423cf29387350d2e28cc691785135613408edb73c79f5d965dbb30e5", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu126-x86_64-linux": { - "hash": "sha256-a3d81f82f9cfe9d8a6d46758758b3a1b3055d902f41917b4ef2976373db843d6", + "hash": "sha256-fb95eb2faee971ebc0ede12678816c7796b64c723e4fd787aea97397f1c7f5cd", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu118-x86_64-linux": { - "hash": "sha256-f1de67e17944a9816f778c72ae73bbbc90d795cb4885c2f9ee5e0b9a3c57583b", + "hash": "sha256-027930f857347a4f1524fa37244c41c53ffb8c1ebd4eeb72fa32eea4a28b8787", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu124-x86_64-linux": { - "hash": "sha256-789b50d767a5121a7e5a52eaf0c8e897bf1787f049ca08faffb220e5053a5f10", + "hash": "sha256-59ee042d58d57100c415f491a3db905671e094707f786f5f7e3260d5b827ad6a", + "hash_type": "git_lfs_concat" + }, + "torch26-cxx98-cu126-aarch64-linux": { + "hash": "sha256-1f9d739bd8198c330b1f2893e0301740c54fa95272233fadb7a95c9b53a70383", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu126-x86_64-linux": { - "hash": "sha256-7c7fe57fea7b9be253085d506f01b2487b2306f22bdffe1de44397fc9f8a3613", + "hash": "sha256-f56c5ea702982b9f75dedeb3a8998550b1b38bcacd77590926234e221fcc571f", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu118-x86_64-linux": { + "hash": "sha256-9c6f2b7fea5327abee2920da86dd57878d5f35aacacc886875050649073d1565", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu126-aarch64-linux": { + "hash": "sha256-fba9bd51e4aa5515ed81193743512dec2129f38555a16a54710e650a717259a8", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu126-x86_64-linux": { + "hash": "sha256-990b615c4b5d2f96874e7f88767681544d84771f3a11443cf0c994759f5e5f75", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu128-aarch64-linux": { + "hash": "sha256-6ad809543e1099f91b022f1393fe9a4527957b854cdfe6c8f4a0632c5497cb9d", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu128-x86_64-linux": { + "hash": "sha256-90aaa73d93db015c693a4089f2574c2ec2d4943bcee5c9b0ede2834a2c72c370", "hash_type": "git_lfs_concat" } } }, { "repo_id": "kernels-community/rotary", - "sha": "4db658e027ec752840bb3f557ee076413b8db03f", + "sha": "804a326b61f181778b5eb4ebe27aecdb8fbcd845", "variants": { "torch25-cxx11-cu118-x86_64-linux": { - "hash": "sha256-907df2035267a65793985bb7f69fb2a975955fb08c2bbc78c58def43d02801da", + "hash": "sha256-198c67cc7330535da671086c3b6a0dd6189015381f25b409704b51224b25ae3c", "hash_type": "git_lfs_concat" }, "torch25-cxx11-cu121-x86_64-linux": { - "hash": "sha256-b614735ae61ee2c1825a3c823fa0cdd3aa07d0bb3f4106001b9e1a557c0ca9b9", + "hash": "sha256-c2e8233d79dd36fc778502c0d44e7399907c2ef064981c7d122fb0652c71eca5", "hash_type": "git_lfs_concat" }, "torch25-cxx11-cu124-x86_64-linux": { - "hash": "sha256-f2e98ec72faaebc1cae25f83ccdbb151868b6902fb5a0623e09d700a514c2a7e", + "hash": "sha256-452040cd5c335a3985da635a76db60a6fc0d9f8b1050fdf29f837d42ee2742ea", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu118-x86_64-linux": { - "hash": "sha256-421214c5a576fac2e0b7998395dccd7f66010f65a6fc647ce06b106ea91105d2", + "hash": "sha256-b627ad5946713c8893f2847eb28f87203f3caaa84f2f35bb9f7b54ea9c3c8a5d", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu121-x86_64-linux": { - "hash": "sha256-9d1c464cf7f391975afa48f2254a639f41582155ad1b50c25bb122418ce8db58", + "hash": "sha256-30311ae1858e29754a4c69e081466e78202ffe8522d08afa46f06350f54cfcd1", "hash_type": "git_lfs_concat" }, "torch25-cxx98-cu124-x86_64-linux": { - "hash": "sha256-82f8012d78304efaa7318f106907630294d10c8b5c9f56923c71df0b03e09f14", + "hash": "sha256-f988c59f5ac640c657f51c7a463f7bcc5ff789109275d8b14f524ad300f9ca55", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu118-x86_64-linux": { - "hash": "sha256-a3247919dcc392efc7e54725dfbce9ee8a796fe4ee53d113048b313de074d3da", + "hash": "sha256-58998893b9992e3ede276388e09c1c31da0b6175d68cf37bcb75bd6f69dba240", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu124-x86_64-linux": { - "hash": "sha256-a21c9734d15946f4cc967d0555d45d7effc6624990c6889fc49162af744fbbe9", + "hash": "sha256-2fdc356b7a5ce2f090dead00253180a750ec9ff72c0afc5f3f07c96e2e603916", + "hash_type": "git_lfs_concat" + }, + "torch26-cxx11-cu126-aarch64-linux": { + "hash": "sha256-d82cd995be25b4b88b0a4086269dcdeb400d0720141fbbfa47bf88cd639ae7e1", "hash_type": "git_lfs_concat" }, "torch26-cxx11-cu126-x86_64-linux": { - "hash": "sha256-01cdda160425b29db0d9bb084874ade4ac081735f9717f272aaefe5bcb379ae1", + "hash": "sha256-a6cd702f278dcbd94f8412d51f79a2664844217b7344bdd24353760c72a789d5", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu118-x86_64-linux": { - "hash": "sha256-17be5b770418ad47101c49d8945b5aa32af9eb5a840bdffb0514d0e264edd860", + "hash": "sha256-c759c2e38a17ea61446afb881cfa2a152d82350e6d38efecbec8ebe1e27cf81f", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu124-x86_64-linux": { - "hash": "sha256-3cd4b9f63cc903e01325b7e5b204e40fc6600c0685f2e19e6f1fa604a599d82d", + "hash": "sha256-d81512fa75acbe8a124b9890bb041fdd1e447794ee210bbb5d01343bd5033eec", + "hash_type": "git_lfs_concat" + }, + "torch26-cxx98-cu126-aarch64-linux": { + "hash": "sha256-a81df695a1b980f899df3c05920a04ff15a89dd28c8cef4067e4e6579669292b", "hash_type": "git_lfs_concat" }, "torch26-cxx98-cu126-x86_64-linux": { - "hash": "sha256-c569f4a4f9b64792507c58d7cfa31dde1285b52125ef07cc98d9f23636af09ca", + "hash": "sha256-868a4b47368a251018bf8f67f3effd8685fed6b01e64725da7e653d38831b166", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu118-x86_64-linux": { + "hash": "sha256-21ae5790dcf3936b66cd74641f815280ea648dffdc5259b7e1dba3fa5a8fc70d", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu126-aarch64-linux": { + "hash": "sha256-93466448e31897ef7db0e84e7d6d36824661b15a9841e2476ff181e1eab155c2", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu126-x86_64-linux": { + "hash": "sha256-e0ce52422c82c2ce966c44e61e0d65c789b36feaaeca818f88c2e746201cde9b", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu128-aarch64-linux": { + "hash": "sha256-eb155e56df00ad7d6455f1549d072c39f14c2b7e355f729bf35cb3e62d087df9", + "hash_type": "git_lfs_concat" + }, + "torch27-cxx11-cu128-x86_64-linux": { + "hash": "sha256-63b3f8fc56c940d824cdf06d3cc5b504d82c14e005c7d2ca5360e384a2b16af2", "hash_type": "git_lfs_concat" } } diff --git a/server/pyproject.toml b/server/pyproject.toml index 53347f52..5489b19d 100644 --- a/server/pyproject.toml +++ b/server/pyproject.toml @@ -9,6 +9,8 @@ authors = [ {name = "Nicolas Patry", email = "nicolas@huggingface.co"}, ] dependencies = [ + # Remove explicit click dependency once typer/click are compatible again. + "click<8.2.0", "einops>=0.8.0", "grpc-interceptor>=0.15.4", "grpcio>=1.67.0", @@ -37,16 +39,16 @@ dependencies = [ ] [[tool.uv.index]] -name = "pytorch-cu124" -url = "https://download.pytorch.org/whl/cu124" +name = "pytorch-cu128" +url = "https://download.pytorch.org/whl/cu128" explicit = true [tool.uv.sources] torch = [ - { index = "pytorch-cu124", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { index = "pytorch-cu128", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, ] torchvision = [ - { index = "pytorch-cu124", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { index = "pytorch-cu128", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, ] [build-system] @@ -92,8 +94,8 @@ gen = [ "mypy-protobuf>=3.6.0", ] torch = [ - "torch==2.6.0", - "torchvision==0.21.0", + "torch==2.7.0", + "torchvision==0.22.0", ] [tool.pytest.ini_options] diff --git a/server/requirements_cuda.txt b/server/requirements_cuda.txt index 0764bf92..a70d893b 100644 --- a/server/requirements_cuda.txt +++ b/server/requirements_cuda.txt @@ -1,43 +1,43 @@ # This file was autogenerated by uv via the following command: -# uv pip compile pyproject.toml --extra attention --extra bnb --extra accelerate --extra compressed-tensors --extra marlin --extra moe --extra quantize --extra peft --extra outlines -o requirements_cuda.txt --python-version 3.11 -accelerate==1.3.0 +# uv pip compile pyproject.toml --extra bnb --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_cuda.txt --python-version 3.11 +accelerate==1.6.0 # via # text-generation-server (pyproject.toml) # peft -aiohappyeyeballs==2.4.4 +aiohappyeyeballs==2.6.1 # via aiohttp -aiohttp==3.11.11 +aiohttp==3.11.18 # via # datasets # fsspec aiosignal==1.3.2 # via aiohttp -airportsdata==20241001 +airportsdata==20250224 # via outlines annotated-types==0.7.0 # via pydantic -attention-kernels @ https://github.com/danieldk/attention-kernels/releases/download/v0.2.0.post2/attention_kernels-0.2.0.post2+cu123torch2.5-cp39-abi3-linux_x86_64.whl - # via text-generation-server (pyproject.toml) -attrs==25.1.0 +attrs==25.3.0 # via # aiohttp # jsonschema # referencing -bitsandbytes==0.45.1 +bitsandbytes==0.45.5 # via text-generation-server (pyproject.toml) -certifi==2024.8.30 +certifi==2025.4.26 # via requests -charset-normalizer==3.4.0 +charset-normalizer==3.4.2 # via requests -click==8.1.7 - # via typer +click==8.1.8 + # via + # text-generation-server (pyproject.toml) + # typer cloudpickle==3.1.1 # via outlines -compressed-tensors==0.9.1 +compressed-tensors==0.9.4 # via text-generation-server (pyproject.toml) datasets==2.21.0 # via text-generation-server (pyproject.toml) -deprecated==1.2.14 +deprecated==1.2.18 # via # opentelemetry-api # opentelemetry-exporter-otlp-proto-grpc @@ -49,15 +49,15 @@ dill==0.3.8 # multiprocess diskcache==5.6.3 # via outlines -einops==0.8.0 +einops==0.8.1 # via text-generation-server (pyproject.toml) -filelock==3.16.1 +filelock==3.18.0 # via # datasets # huggingface-hub # torch # transformers -frozenlist==1.5.0 +frozenlist==1.6.0 # via # aiohttp # aiosignal @@ -68,30 +68,36 @@ fsspec==2024.6.1 # torch genson==1.3.0 # via outlines -googleapis-common-protos==1.65.0 +googleapis-common-protos==1.70.0 # via # grpcio-status # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http grpc-interceptor==0.15.4 # via text-generation-server (pyproject.toml) -grpcio==1.68.0 +grpcio==1.71.0 # via # text-generation-server (pyproject.toml) # grpc-interceptor # grpcio-reflection # grpcio-status # opentelemetry-exporter-otlp-proto-grpc -grpcio-reflection==1.68.0 +grpcio-reflection==1.71.0 # via text-generation-server (pyproject.toml) -grpcio-status==1.68.0 +grpcio-status==1.71.0 # via text-generation-server (pyproject.toml) -hf-transfer==0.1.8 +hf-transfer==0.1.9 # via text-generation-server (pyproject.toml) -huggingface-hub==0.28.1 +hf-xet==1.1.0 # via + # text-generation-server (pyproject.toml) + # huggingface-hub +huggingface-hub==0.31.1 + # via + # text-generation-server (pyproject.toml) # accelerate # datasets + # kernels # peft # tokenizers # transformers @@ -99,13 +105,15 @@ idna==3.10 # via # requests # yarl -importlib-metadata==7.1.0 +importlib-metadata==8.6.1 # via opentelemetry-api interegular==0.3.3 # via # outlines # outlines-core -jinja2==3.1.5 +iso3166==2.1.1 + # via outlines +jinja2==3.1.6 # via # outlines # torch @@ -113,8 +121,10 @@ jsonschema==4.23.0 # via # outlines # outlines-core -jsonschema-specifications==2024.10.1 +jsonschema-specifications==2025.4.1 # via jsonschema +kernels==0.5.0 + # via text-generation-server (pyproject.toml) lark==1.2.2 # via outlines loguru==0.7.3 @@ -123,15 +133,11 @@ markdown-it-py==3.0.0 # via rich markupsafe==3.0.2 # via jinja2 -marlin-kernels @ https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp311-cp311-linux_x86_64.whl - # via text-generation-server (pyproject.toml) mdurl==0.1.2 # via markdown-it-py -moe-kernels @ https://github.com/danieldk/moe-kernels/releases/download/v0.8.2/moe_kernels-0.8.2+cu123torch2.5-cp39-abi3-linux_x86_64.whl - # via text-generation-server (pyproject.toml) mpmath==1.3.0 # via sympy -multidict==6.1.0 +multidict==6.4.3 # via # aiohttp # yarl @@ -141,7 +147,7 @@ nest-asyncio==1.6.0 # via outlines networkx==3.4.2 # via torch -numpy==1.26.4 +numpy==2.2.5 # via # text-generation-server (pyproject.toml) # accelerate @@ -152,43 +158,44 @@ numpy==1.26.4 # peft # scipy # transformers -nvidia-cublas-cu12==12.4.5.8 +nvidia-cublas-cu12==12.6.4.1 # via # nvidia-cudnn-cu12 # nvidia-cusolver-cu12 # torch -nvidia-cuda-cupti-cu12==12.4.127 +nvidia-cuda-cupti-cu12==12.6.80 # via torch -nvidia-cuda-nvrtc-cu12==12.4.127 +nvidia-cuda-nvrtc-cu12==12.6.77 # via torch -nvidia-cuda-runtime-cu12==12.4.127 +nvidia-cuda-runtime-cu12==12.6.77 # via torch -nvidia-cudnn-cu12==9.1.0.70 +nvidia-cudnn-cu12==9.5.1.17 # via torch -nvidia-cufft-cu12==11.2.1.3 +nvidia-cufft-cu12==11.3.0.4 # via torch -nvidia-curand-cu12==10.3.5.147 +nvidia-cufile-cu12==1.11.1.6 # via torch -nvidia-cusolver-cu12==11.6.1.9 +nvidia-curand-cu12==10.3.7.77 # via torch -nvidia-cusparse-cu12==12.3.1.170 +nvidia-cusolver-cu12==11.7.1.2 + # via torch +nvidia-cusparse-cu12==12.5.4.2 # via # nvidia-cusolver-cu12 # torch -nvidia-cusparselt-cu12==0.6.2 +nvidia-cusparselt-cu12==0.6.3 # via torch -nvidia-ml-py==12.570.86 - # via moe-kernels -nvidia-nccl-cu12==2.21.5 +nvidia-nccl-cu12==2.26.2 # via torch -nvidia-nvjitlink-cu12==12.4.127 +nvidia-nvjitlink-cu12==12.6.85 # via + # nvidia-cufft-cu12 # nvidia-cusolver-cu12 # nvidia-cusparse-cu12 # torch -nvidia-nvtx-cu12==12.4.127 +nvidia-nvtx-cu12==12.6.77 # via torch -opentelemetry-api==1.30.0 +opentelemetry-api==1.33.0 # via # text-generation-server (pyproject.toml) # opentelemetry-exporter-otlp-proto-grpc @@ -197,86 +204,85 @@ opentelemetry-api==1.30.0 # opentelemetry-instrumentation-grpc # opentelemetry-sdk # opentelemetry-semantic-conventions -opentelemetry-exporter-otlp==1.30.0 +opentelemetry-exporter-otlp==1.33.0 # via text-generation-server (pyproject.toml) -opentelemetry-exporter-otlp-proto-common==1.30.0 +opentelemetry-exporter-otlp-proto-common==1.33.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-exporter-otlp-proto-grpc==1.30.0 +opentelemetry-exporter-otlp-proto-grpc==1.33.0 # via opentelemetry-exporter-otlp -opentelemetry-exporter-otlp-proto-http==1.30.0 +opentelemetry-exporter-otlp-proto-http==1.33.0 # via opentelemetry-exporter-otlp -opentelemetry-instrumentation==0.51b0 +opentelemetry-instrumentation==0.54b0 # via opentelemetry-instrumentation-grpc -opentelemetry-instrumentation-grpc==0.51b0 +opentelemetry-instrumentation-grpc==0.54b0 # via text-generation-server (pyproject.toml) -opentelemetry-proto==1.30.0 +opentelemetry-proto==1.33.0 # via # opentelemetry-exporter-otlp-proto-common # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-sdk==1.30.0 +opentelemetry-sdk==1.33.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-semantic-conventions==0.51b0 +opentelemetry-semantic-conventions==0.54b0 # via # opentelemetry-instrumentation # opentelemetry-instrumentation-grpc # opentelemetry-sdk -outlines==0.1.14 +outlines==0.2.3 # via text-generation-server (pyproject.toml) outlines-core==0.1.26 # via outlines -packaging==24.1 +packaging==25.0 # via # accelerate # datasets # huggingface-hub + # kernels # opentelemetry-instrumentation # peft # transformers pandas==2.2.3 # via datasets -peft==0.14.0 +peft==0.15.2 # via text-generation-server (pyproject.toml) -pillow==11.1.0 +pillow==11.2.1 # via text-generation-server (pyproject.toml) prometheus-client==0.21.1 # via text-generation-server (pyproject.toml) -propcache==0.2.1 +propcache==0.3.1 # via # aiohttp # yarl -protobuf==5.29.3 +protobuf==5.29.4 # via # text-generation-server (pyproject.toml) # googleapis-common-protos # grpcio-reflection # grpcio-status # opentelemetry-proto -psutil==6.1.1 +psutil==7.0.0 # via # accelerate # peft py-cpuinfo==9.0.0 # via text-generation-server (pyproject.toml) -pyarrow==19.0.0 +pyarrow==20.0.0 # via datasets -pycountry==24.6.1 - # via outlines -pydantic==2.10.6 +pydantic==2.11.4 # via # compressed-tensors # outlines -pydantic-core==2.27.2 +pydantic-core==2.33.2 # via pydantic -pygments==2.18.0 +pygments==2.19.1 # via rich python-dateutil==2.9.0.post0 # via pandas -pytz==2025.1 +pytz==2025.2 # via pandas pyyaml==6.0.2 # via @@ -290,7 +296,7 @@ referencing==0.36.2 # jsonschema # jsonschema-specifications # outlines -regex==2024.9.11 +regex==2024.11.6 # via transformers requests==2.32.3 # via @@ -299,65 +305,62 @@ requests==2.32.3 # opentelemetry-exporter-otlp-proto-http # outlines # transformers -rich==13.9.4 +rich==14.0.0 # via # text-generation-server (pyproject.toml) # typer -rpds-py==0.22.3 +rpds-py==0.24.0 # via # jsonschema # referencing -safetensors==0.4.5 +safetensors==0.5.3 # via # text-generation-server (pyproject.toml) # accelerate # peft # transformers -scipy==1.13.1 +scipy==1.15.3 # via text-generation-server (pyproject.toml) sentencepiece==0.2.0 # via text-generation-server (pyproject.toml) +setuptools==80.4.0 + # via triton shellingham==1.5.4 # via typer six==1.17.0 # via python-dateutil -sympy==1.13.1 +sympy==1.14.0 # via torch texttable==1.7.0 # via text-generation-server (pyproject.toml) -tokenizers==0.21.0 +tokenizers==0.21.1 # via # text-generation-server (pyproject.toml) # transformers -torch==2.6.0 +torch==2.7.0 # via # accelerate - # attention-kernels # bitsandbytes # compressed-tensors - # marlin-kernels - # moe-kernels # outlines # peft -tqdm==4.66.5 +tqdm==4.67.1 # via # datasets # huggingface-hub # outlines # peft # transformers -transformers==4.49 +transformers==4.51.3 # via # text-generation-server (pyproject.toml) # compressed-tensors # peft -triton==3.2.0 - # via - # moe-kernels - # torch -typer==0.15.1 +triton==3.3.0 + # via torch +typer==0.15.3 # via text-generation-server (pyproject.toml) -typing-extensions==4.12.2 +typing-extensions==4.13.2 # via # huggingface-hub # opentelemetry-sdk @@ -367,18 +370,21 @@ typing-extensions==4.12.2 # referencing # torch # typer -tzdata==2025.1 + # typing-inspection +typing-inspection==0.4.0 + # via pydantic +tzdata==2025.2 # via pandas -urllib3==2.2.3 +urllib3==2.4.0 # via requests -wrapt==1.16.0 +wrapt==1.17.2 # via # deprecated # opentelemetry-instrumentation # opentelemetry-instrumentation-grpc xxhash==3.5.0 # via datasets -yarl==1.18.3 +yarl==1.20.0 # via aiohttp -zipp==3.20.2 +zipp==3.21.0 # via importlib-metadata diff --git a/server/requirements_gen.txt b/server/requirements_gen.txt index 6d64a34b..0cee5d6c 100644 --- a/server/requirements_gen.txt +++ b/server/requirements_gen.txt @@ -1,33 +1,35 @@ # This file was autogenerated by uv via the following command: # uv pip compile pyproject.toml --extra gen -o requirements_gen.txt --python-version 3.11 -certifi==2025.1.31 +certifi==2025.4.26 # via requests -charset-normalizer==3.4.1 +charset-normalizer==3.4.2 # via requests click==8.1.8 - # via typer + # via + # text-generation-server (pyproject.toml) + # typer deprecated==1.2.18 # via # opentelemetry-api # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http # opentelemetry-semantic-conventions -einops==0.8.0 +einops==0.8.1 # via text-generation-server (pyproject.toml) -filelock==3.17.0 +filelock==3.18.0 # via # huggingface-hub # transformers -fsspec==2025.2.0 +fsspec==2025.3.2 # via huggingface-hub -googleapis-common-protos==1.66.0 +googleapis-common-protos==1.70.0 # via # grpcio-status # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http grpc-interceptor==0.15.4 # via text-generation-server (pyproject.toml) -grpcio==1.70.0 +grpcio==1.71.0 # via # text-generation-server (pyproject.toml) # grpc-interceptor @@ -35,22 +37,30 @@ grpcio==1.70.0 # grpcio-status # grpcio-tools # opentelemetry-exporter-otlp-proto-grpc -grpcio-reflection==1.70.0 +grpcio-reflection==1.71.0 # via text-generation-server (pyproject.toml) -grpcio-status==1.70.0 +grpcio-status==1.71.0 # via text-generation-server (pyproject.toml) -grpcio-tools==1.70.0 +grpcio-tools==1.71.0 # via text-generation-server (pyproject.toml) hf-transfer==0.1.9 # via text-generation-server (pyproject.toml) -huggingface-hub==0.28.1 +hf-xet==1.1.0 # via + # text-generation-server (pyproject.toml) + # huggingface-hub +huggingface-hub==0.31.1 + # via + # text-generation-server (pyproject.toml) + # kernels # tokenizers # transformers idna==3.10 # via requests -importlib-metadata==8.5.0 +importlib-metadata==8.6.1 # via opentelemetry-api +kernels==0.5.0 + # via text-generation-server (pyproject.toml) loguru==0.7.3 # via text-generation-server (pyproject.toml) markdown-it-py==3.0.0 @@ -59,12 +69,12 @@ mdurl==0.1.2 # via markdown-it-py mypy-protobuf==3.6.0 # via text-generation-server (pyproject.toml) -numpy==2.2.2 +numpy==2.2.5 # via # text-generation-server (pyproject.toml) # scipy # transformers -opentelemetry-api==1.30.0 +opentelemetry-api==1.33.0 # via # text-generation-server (pyproject.toml) # opentelemetry-exporter-otlp-proto-grpc @@ -73,44 +83,45 @@ opentelemetry-api==1.30.0 # opentelemetry-instrumentation-grpc # opentelemetry-sdk # opentelemetry-semantic-conventions -opentelemetry-exporter-otlp==1.30.0 +opentelemetry-exporter-otlp==1.33.0 # via text-generation-server (pyproject.toml) -opentelemetry-exporter-otlp-proto-common==1.30.0 +opentelemetry-exporter-otlp-proto-common==1.33.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-exporter-otlp-proto-grpc==1.30.0 +opentelemetry-exporter-otlp-proto-grpc==1.33.0 # via opentelemetry-exporter-otlp -opentelemetry-exporter-otlp-proto-http==1.30.0 +opentelemetry-exporter-otlp-proto-http==1.33.0 # via opentelemetry-exporter-otlp -opentelemetry-instrumentation==0.51b0 +opentelemetry-instrumentation==0.54b0 # via opentelemetry-instrumentation-grpc -opentelemetry-instrumentation-grpc==0.51b0 +opentelemetry-instrumentation-grpc==0.54b0 # via text-generation-server (pyproject.toml) -opentelemetry-proto==1.30.0 +opentelemetry-proto==1.33.0 # via # opentelemetry-exporter-otlp-proto-common # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-sdk==1.30.0 +opentelemetry-sdk==1.33.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-semantic-conventions==0.51b0 +opentelemetry-semantic-conventions==0.54b0 # via # opentelemetry-instrumentation # opentelemetry-instrumentation-grpc # opentelemetry-sdk -packaging==24.2 +packaging==25.0 # via # huggingface-hub + # kernels # opentelemetry-instrumentation # transformers -pillow==11.1.0 +pillow==11.2.1 # via text-generation-server (pyproject.toml) prometheus-client==0.21.1 # via text-generation-server (pyproject.toml) -protobuf==5.29.3 +protobuf==5.29.4 # via # text-generation-server (pyproject.toml) # googleapis-common-protos @@ -134,23 +145,23 @@ requests==2.32.3 # huggingface-hub # opentelemetry-exporter-otlp-proto-http # transformers -rich==13.9.4 +rich==14.0.0 # via # text-generation-server (pyproject.toml) # typer -safetensors==0.5.2 +safetensors==0.5.3 # via # text-generation-server (pyproject.toml) # transformers -scipy==1.15.1 +scipy==1.15.3 # via text-generation-server (pyproject.toml) sentencepiece==0.2.0 # via text-generation-server (pyproject.toml) -setuptools==75.8.0 +setuptools==80.4.0 # via grpcio-tools shellingham==1.5.4 # via typer -tokenizers==0.21.0 +tokenizers==0.21.1 # via # text-generation-server (pyproject.toml) # transformers @@ -158,18 +169,18 @@ tqdm==4.67.1 # via # huggingface-hub # transformers -transformers==4.49 +transformers==4.51.3 # via text-generation-server (pyproject.toml) -typer==0.15.1 +typer==0.15.3 # via text-generation-server (pyproject.toml) -types-protobuf==5.29.1.20241207 +types-protobuf==6.30.2.20250506 # via mypy-protobuf -typing-extensions==4.12.2 +typing-extensions==4.13.2 # via # huggingface-hub # opentelemetry-sdk # typer -urllib3==2.3.0 +urllib3==2.4.0 # via requests wrapt==1.17.2 # via diff --git a/server/requirements_intel.txt b/server/requirements_intel.txt index c671199f..0cad583c 100644 --- a/server/requirements_intel.txt +++ b/server/requirements_intel.txt @@ -1,39 +1,41 @@ # This file was autogenerated by uv via the following command: # uv pip compile pyproject.toml --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_intel.txt --python-version 3.11 -accelerate==1.3.0 +accelerate==1.6.0 # via # text-generation-server (pyproject.toml) # peft -aiohappyeyeballs==2.4.4 +aiohappyeyeballs==2.6.1 # via aiohttp -aiohttp==3.11.11 +aiohttp==3.11.18 # via # datasets # fsspec aiosignal==1.3.2 # via aiohttp -airportsdata==20241001 +airportsdata==20250224 # via outlines annotated-types==0.7.0 # via pydantic -attrs==25.1.0 +attrs==25.3.0 # via # aiohttp # jsonschema # referencing -certifi==2024.8.30 +certifi==2025.4.26 # via requests -charset-normalizer==3.4.0 +charset-normalizer==3.4.2 # via requests -click==8.1.7 - # via typer +click==8.1.8 + # via + # text-generation-server (pyproject.toml) + # typer cloudpickle==3.1.1 # via outlines -compressed-tensors==0.9.1 +compressed-tensors==0.9.4 # via text-generation-server (pyproject.toml) datasets==2.21.0 # via text-generation-server (pyproject.toml) -deprecated==1.2.14 +deprecated==1.2.18 # via # opentelemetry-api # opentelemetry-exporter-otlp-proto-grpc @@ -45,15 +47,15 @@ dill==0.3.8 # multiprocess diskcache==5.6.3 # via outlines -einops==0.8.0 +einops==0.8.1 # via text-generation-server (pyproject.toml) -filelock==3.16.1 +filelock==3.18.0 # via # datasets # huggingface-hub # torch # transformers -frozenlist==1.5.0 +frozenlist==1.6.0 # via # aiohttp # aiosignal @@ -64,30 +66,36 @@ fsspec==2024.6.1 # torch genson==1.3.0 # via outlines -googleapis-common-protos==1.65.0 +googleapis-common-protos==1.70.0 # via # grpcio-status # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http grpc-interceptor==0.15.4 # via text-generation-server (pyproject.toml) -grpcio==1.68.0 +grpcio==1.71.0 # via # text-generation-server (pyproject.toml) # grpc-interceptor # grpcio-reflection # grpcio-status # opentelemetry-exporter-otlp-proto-grpc -grpcio-reflection==1.68.0 +grpcio-reflection==1.71.0 # via text-generation-server (pyproject.toml) -grpcio-status==1.68.0 +grpcio-status==1.71.0 # via text-generation-server (pyproject.toml) -hf-transfer==0.1.8 +hf-transfer==0.1.9 # via text-generation-server (pyproject.toml) -huggingface-hub==0.28.1 +hf-xet==1.1.0 # via + # text-generation-server (pyproject.toml) + # huggingface-hub +huggingface-hub==0.31.1 + # via + # text-generation-server (pyproject.toml) # accelerate # datasets + # kernels # peft # tokenizers # transformers @@ -95,13 +103,15 @@ idna==3.10 # via # requests # yarl -importlib-metadata==7.1.0 +importlib-metadata==8.6.1 # via opentelemetry-api interegular==0.3.3 # via # outlines # outlines-core -jinja2==3.1.5 +iso3166==2.1.1 + # via outlines +jinja2==3.1.6 # via # outlines # torch @@ -109,8 +119,10 @@ jsonschema==4.23.0 # via # outlines # outlines-core -jsonschema-specifications==2024.10.1 +jsonschema-specifications==2025.4.1 # via jsonschema +kernels==0.5.0 + # via text-generation-server (pyproject.toml) lark==1.2.2 # via outlines loguru==0.7.3 @@ -123,7 +135,7 @@ mdurl==0.1.2 # via markdown-it-py mpmath==1.3.0 # via sympy -multidict==6.1.0 +multidict==6.4.3 # via # aiohttp # yarl @@ -133,7 +145,7 @@ nest-asyncio==1.6.0 # via outlines networkx==3.4.2 # via torch -numpy==1.26.4 +numpy==2.2.5 # via # text-generation-server (pyproject.toml) # accelerate @@ -143,41 +155,44 @@ numpy==1.26.4 # peft # scipy # transformers -nvidia-cublas-cu12==12.4.5.8 +nvidia-cublas-cu12==12.6.4.1 # via # nvidia-cudnn-cu12 # nvidia-cusolver-cu12 # torch -nvidia-cuda-cupti-cu12==12.4.127 +nvidia-cuda-cupti-cu12==12.6.80 # via torch -nvidia-cuda-nvrtc-cu12==12.4.127 +nvidia-cuda-nvrtc-cu12==12.6.77 # via torch -nvidia-cuda-runtime-cu12==12.4.127 +nvidia-cuda-runtime-cu12==12.6.77 # via torch -nvidia-cudnn-cu12==9.1.0.70 +nvidia-cudnn-cu12==9.5.1.17 # via torch -nvidia-cufft-cu12==11.2.1.3 +nvidia-cufft-cu12==11.3.0.4 # via torch -nvidia-curand-cu12==10.3.5.147 +nvidia-cufile-cu12==1.11.1.6 # via torch -nvidia-cusolver-cu12==11.6.1.9 +nvidia-curand-cu12==10.3.7.77 # via torch -nvidia-cusparse-cu12==12.3.1.170 +nvidia-cusolver-cu12==11.7.1.2 + # via torch +nvidia-cusparse-cu12==12.5.4.2 # via # nvidia-cusolver-cu12 # torch -nvidia-cusparselt-cu12==0.6.2 +nvidia-cusparselt-cu12==0.6.3 # via torch -nvidia-nccl-cu12==2.21.5 +nvidia-nccl-cu12==2.26.2 # via torch -nvidia-nvjitlink-cu12==12.4.127 +nvidia-nvjitlink-cu12==12.6.85 # via + # nvidia-cufft-cu12 # nvidia-cusolver-cu12 # nvidia-cusparse-cu12 # torch -nvidia-nvtx-cu12==12.4.127 +nvidia-nvtx-cu12==12.6.77 # via torch -opentelemetry-api==1.30.0 +opentelemetry-api==1.33.0 # via # text-generation-server (pyproject.toml) # opentelemetry-exporter-otlp-proto-grpc @@ -186,86 +201,85 @@ opentelemetry-api==1.30.0 # opentelemetry-instrumentation-grpc # opentelemetry-sdk # opentelemetry-semantic-conventions -opentelemetry-exporter-otlp==1.30.0 +opentelemetry-exporter-otlp==1.33.0 # via text-generation-server (pyproject.toml) -opentelemetry-exporter-otlp-proto-common==1.30.0 +opentelemetry-exporter-otlp-proto-common==1.33.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-exporter-otlp-proto-grpc==1.30.0 +opentelemetry-exporter-otlp-proto-grpc==1.33.0 # via opentelemetry-exporter-otlp -opentelemetry-exporter-otlp-proto-http==1.30.0 +opentelemetry-exporter-otlp-proto-http==1.33.0 # via opentelemetry-exporter-otlp -opentelemetry-instrumentation==0.51b0 +opentelemetry-instrumentation==0.54b0 # via opentelemetry-instrumentation-grpc -opentelemetry-instrumentation-grpc==0.51b0 +opentelemetry-instrumentation-grpc==0.54b0 # via text-generation-server (pyproject.toml) -opentelemetry-proto==1.30.0 +opentelemetry-proto==1.33.0 # via # opentelemetry-exporter-otlp-proto-common # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-sdk==1.30.0 +opentelemetry-sdk==1.33.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-semantic-conventions==0.51b0 +opentelemetry-semantic-conventions==0.54b0 # via # opentelemetry-instrumentation # opentelemetry-instrumentation-grpc # opentelemetry-sdk -outlines==0.1.14 +outlines==0.2.3 # via text-generation-server (pyproject.toml) outlines-core==0.1.26 # via outlines -packaging==24.1 +packaging==25.0 # via # accelerate # datasets # huggingface-hub + # kernels # opentelemetry-instrumentation # peft # transformers pandas==2.2.3 # via datasets -peft==0.14.0 +peft==0.15.2 # via text-generation-server (pyproject.toml) -pillow==11.1.0 +pillow==11.2.1 # via text-generation-server (pyproject.toml) prometheus-client==0.21.1 # via text-generation-server (pyproject.toml) -propcache==0.2.1 +propcache==0.3.1 # via # aiohttp # yarl -protobuf==5.29.3 +protobuf==5.29.4 # via # text-generation-server (pyproject.toml) # googleapis-common-protos # grpcio-reflection # grpcio-status # opentelemetry-proto -psutil==6.1.1 +psutil==7.0.0 # via # accelerate # peft py-cpuinfo==9.0.0 # via text-generation-server (pyproject.toml) -pyarrow==19.0.0 +pyarrow==20.0.0 # via datasets -pycountry==24.6.1 - # via outlines -pydantic==2.10.6 +pydantic==2.11.4 # via # compressed-tensors # outlines -pydantic-core==2.27.2 +pydantic-core==2.33.2 # via pydantic -pygments==2.18.0 +pygments==2.19.1 # via rich python-dateutil==2.9.0.post0 # via pandas -pytz==2025.1 +pytz==2025.2 # via pandas pyyaml==6.0.2 # via @@ -279,7 +293,7 @@ referencing==0.36.2 # jsonschema # jsonschema-specifications # outlines -regex==2024.9.11 +regex==2024.11.6 # via transformers requests==2.32.3 # via @@ -288,59 +302,61 @@ requests==2.32.3 # opentelemetry-exporter-otlp-proto-http # outlines # transformers -rich==13.9.4 +rich==14.0.0 # via # text-generation-server (pyproject.toml) # typer -rpds-py==0.22.3 +rpds-py==0.24.0 # via # jsonschema # referencing -safetensors==0.4.5 +safetensors==0.5.3 # via # text-generation-server (pyproject.toml) # accelerate # peft # transformers -scipy==1.13.1 +scipy==1.15.3 # via text-generation-server (pyproject.toml) sentencepiece==0.2.0 # via text-generation-server (pyproject.toml) +setuptools==80.4.0 + # via triton shellingham==1.5.4 # via typer six==1.17.0 # via python-dateutil -sympy==1.13.1 +sympy==1.14.0 # via torch texttable==1.7.0 # via text-generation-server (pyproject.toml) -tokenizers==0.21.0 +tokenizers==0.21.1 # via # text-generation-server (pyproject.toml) # transformers -torch==2.6.0 +torch==2.7.0 # via # accelerate # compressed-tensors # outlines # peft -tqdm==4.66.5 +tqdm==4.67.1 # via # datasets # huggingface-hub # outlines # peft # transformers -transformers==4.49 +transformers==4.51.3 # via # text-generation-server (pyproject.toml) # compressed-tensors # peft -triton==3.2.0 +triton==3.3.0 # via torch -typer==0.15.1 +typer==0.15.3 # via text-generation-server (pyproject.toml) -typing-extensions==4.12.2 +typing-extensions==4.13.2 # via # huggingface-hub # opentelemetry-sdk @@ -350,18 +366,21 @@ typing-extensions==4.12.2 # referencing # torch # typer -tzdata==2025.1 + # typing-inspection +typing-inspection==0.4.0 + # via pydantic +tzdata==2025.2 # via pandas -urllib3==2.2.3 +urllib3==2.4.0 # via requests -wrapt==1.16.0 +wrapt==1.17.2 # via # deprecated # opentelemetry-instrumentation # opentelemetry-instrumentation-grpc xxhash==3.5.0 # via datasets -yarl==1.18.3 +yarl==1.20.0 # via aiohttp -zipp==3.20.2 +zipp==3.21.0 # via importlib-metadata diff --git a/server/requirements_rocm.txt b/server/requirements_rocm.txt index fe7ca572..1f71c8e6 100644 --- a/server/requirements_rocm.txt +++ b/server/requirements_rocm.txt @@ -1,39 +1,41 @@ # This file was autogenerated by uv via the following command: # uv pip compile pyproject.toml --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_rocm.txt --python-version 3.11 -accelerate==1.3.0 +accelerate==1.6.0 # via # text-generation-server (pyproject.toml) # peft -aiohappyeyeballs==2.4.4 +aiohappyeyeballs==2.6.1 # via aiohttp -aiohttp==3.11.11 +aiohttp==3.11.18 # via # datasets # fsspec aiosignal==1.3.2 # via aiohttp -airportsdata==20241001 +airportsdata==20250224 # via outlines annotated-types==0.7.0 # via pydantic -attrs==25.1.0 +attrs==25.3.0 # via # aiohttp # jsonschema # referencing -certifi==2024.8.30 +certifi==2025.4.26 # via requests -charset-normalizer==3.4.0 +charset-normalizer==3.4.2 # via requests -click==8.1.7 - # via typer +click==8.1.8 + # via + # text-generation-server (pyproject.toml) + # typer cloudpickle==3.1.1 # via outlines -compressed-tensors==0.9.1 +compressed-tensors==0.9.4 # via text-generation-server (pyproject.toml) datasets==2.21.0 # via text-generation-server (pyproject.toml) -deprecated==1.2.14 +deprecated==1.2.18 # via # opentelemetry-api # opentelemetry-exporter-otlp-proto-grpc @@ -45,15 +47,15 @@ dill==0.3.8 # multiprocess diskcache==5.6.3 # via outlines -einops==0.8.0 +einops==0.8.1 # via text-generation-server (pyproject.toml) -filelock==3.16.1 +filelock==3.18.0 # via # datasets # huggingface-hub # torch # transformers -frozenlist==1.5.0 +frozenlist==1.6.0 # via # aiohttp # aiosignal @@ -64,30 +66,36 @@ fsspec==2024.6.1 # torch genson==1.3.0 # via outlines -googleapis-common-protos==1.65.0 +googleapis-common-protos==1.70.0 # via # grpcio-status # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http grpc-interceptor==0.15.4 # via text-generation-server (pyproject.toml) -grpcio==1.68.0 +grpcio==1.71.0 # via # text-generation-server (pyproject.toml) # grpc-interceptor # grpcio-reflection # grpcio-status # opentelemetry-exporter-otlp-proto-grpc -grpcio-reflection==1.68.0 +grpcio-reflection==1.71.0 # via text-generation-server (pyproject.toml) -grpcio-status==1.68.0 +grpcio-status==1.71.0 # via text-generation-server (pyproject.toml) -hf-transfer==0.1.8 +hf-transfer==0.1.9 # via text-generation-server (pyproject.toml) -huggingface-hub==0.28.1 +hf-xet==1.1.0 # via + # text-generation-server (pyproject.toml) + # huggingface-hub +huggingface-hub==0.31.1 + # via + # text-generation-server (pyproject.toml) # accelerate # datasets + # kernels # peft # tokenizers # transformers @@ -95,13 +103,15 @@ idna==3.10 # via # requests # yarl -importlib-metadata==7.1.0 +importlib-metadata==8.6.1 # via opentelemetry-api interegular==0.3.3 # via # outlines # outlines-core -jinja2==3.1.5 +iso3166==2.1.1 + # via outlines +jinja2==3.1.6 # via # outlines # torch @@ -109,8 +119,10 @@ jsonschema==4.23.0 # via # outlines # outlines-core -jsonschema-specifications==2024.10.1 +jsonschema-specifications==2025.4.1 # via jsonschema +kernels==0.5.0 + # via text-generation-server (pyproject.toml) lark==1.2.2 # via outlines loguru==0.7.3 @@ -123,7 +135,7 @@ mdurl==0.1.2 # via markdown-it-py mpmath==1.3.0 # via sympy -multidict==6.1.0 +multidict==6.4.3 # via # aiohttp # yarl @@ -133,7 +145,7 @@ nest-asyncio==1.6.0 # via outlines networkx==3.4.2 # via torch -numpy==1.26.4 +numpy==2.2.5 # via # text-generation-server (pyproject.toml) # accelerate @@ -143,41 +155,44 @@ numpy==1.26.4 # peft # scipy # transformers -nvidia-cublas-cu12==12.4.5.8 +nvidia-cublas-cu12==12.6.4.1 # via # nvidia-cudnn-cu12 # nvidia-cusolver-cu12 # torch -nvidia-cuda-cupti-cu12==12.4.127 +nvidia-cuda-cupti-cu12==12.6.80 # via torch -nvidia-cuda-nvrtc-cu12==12.4.127 +nvidia-cuda-nvrtc-cu12==12.6.77 # via torch -nvidia-cuda-runtime-cu12==12.4.127 +nvidia-cuda-runtime-cu12==12.6.77 # via torch -nvidia-cudnn-cu12==9.1.0.70 +nvidia-cudnn-cu12==9.5.1.17 # via torch -nvidia-cufft-cu12==11.2.1.3 +nvidia-cufft-cu12==11.3.0.4 # via torch -nvidia-curand-cu12==10.3.5.147 +nvidia-cufile-cu12==1.11.1.6 # via torch -nvidia-cusolver-cu12==11.6.1.9 +nvidia-curand-cu12==10.3.7.77 # via torch -nvidia-cusparse-cu12==12.3.1.170 +nvidia-cusolver-cu12==11.7.1.2 + # via torch +nvidia-cusparse-cu12==12.5.4.2 # via # nvidia-cusolver-cu12 # torch -nvidia-cusparselt-cu12==0.6.2 +nvidia-cusparselt-cu12==0.6.3 # via torch -nvidia-nccl-cu12==2.21.5 +nvidia-nccl-cu12==2.26.2 # via torch -nvidia-nvjitlink-cu12==12.4.127 +nvidia-nvjitlink-cu12==12.6.85 # via + # nvidia-cufft-cu12 # nvidia-cusolver-cu12 # nvidia-cusparse-cu12 # torch -nvidia-nvtx-cu12==12.4.127 +nvidia-nvtx-cu12==12.6.77 # via torch -opentelemetry-api==1.30.0 +opentelemetry-api==1.33.0 # via # text-generation-server (pyproject.toml) # opentelemetry-exporter-otlp-proto-grpc @@ -186,86 +201,85 @@ opentelemetry-api==1.30.0 # opentelemetry-instrumentation-grpc # opentelemetry-sdk # opentelemetry-semantic-conventions -opentelemetry-exporter-otlp==1.30.0 +opentelemetry-exporter-otlp==1.33.0 # via text-generation-server (pyproject.toml) -opentelemetry-exporter-otlp-proto-common==1.30.0 +opentelemetry-exporter-otlp-proto-common==1.33.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-exporter-otlp-proto-grpc==1.30.0 +opentelemetry-exporter-otlp-proto-grpc==1.33.0 # via opentelemetry-exporter-otlp -opentelemetry-exporter-otlp-proto-http==1.30.0 +opentelemetry-exporter-otlp-proto-http==1.33.0 # via opentelemetry-exporter-otlp -opentelemetry-instrumentation==0.51b0 +opentelemetry-instrumentation==0.54b0 # via opentelemetry-instrumentation-grpc -opentelemetry-instrumentation-grpc==0.51b0 +opentelemetry-instrumentation-grpc==0.54b0 # via text-generation-server (pyproject.toml) -opentelemetry-proto==1.30.0 +opentelemetry-proto==1.33.0 # via # opentelemetry-exporter-otlp-proto-common # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-sdk==1.30.0 +opentelemetry-sdk==1.33.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-semantic-conventions==0.51b0 +opentelemetry-semantic-conventions==0.54b0 # via # opentelemetry-instrumentation # opentelemetry-instrumentation-grpc # opentelemetry-sdk -outlines==0.1.14 +outlines==0.2.3 # via text-generation-server (pyproject.toml) outlines-core==0.1.26 # via outlines -packaging==24.1 +packaging==25.0 # via # accelerate # datasets # huggingface-hub + # kernels # opentelemetry-instrumentation # peft # transformers pandas==2.2.3 # via datasets -peft==0.14.0 +peft==0.15.2 # via text-generation-server (pyproject.toml) -pillow==11.1.0 +pillow==11.2.1 # via text-generation-server (pyproject.toml) prometheus-client==0.21.1 # via text-generation-server (pyproject.toml) -propcache==0.2.1 +propcache==0.3.1 # via # aiohttp # yarl -protobuf==5.29.3 +protobuf==5.29.4 # via # text-generation-server (pyproject.toml) # googleapis-common-protos # grpcio-reflection # grpcio-status # opentelemetry-proto -psutil==6.1.1 +psutil==7.0.0 # via # accelerate # peft py-cpuinfo==9.0.0 # via text-generation-server (pyproject.toml) -pyarrow==19.0.0 +pyarrow==20.0.0 # via datasets -pycountry==24.6.1 - # via outlines -pydantic==2.10.6 +pydantic==2.11.4 # via # compressed-tensors # outlines -pydantic-core==2.27.2 +pydantic-core==2.33.2 # via pydantic -pygments==2.18.0 +pygments==2.19.1 # via rich python-dateutil==2.9.0.post0 # via pandas -pytz==2025.1 +pytz==2025.2 # via pandas pyyaml==6.0.2 # via @@ -279,7 +293,7 @@ referencing==0.36.2 # jsonschema # jsonschema-specifications # outlines -regex==2024.9.11 +regex==2024.11.6 # via transformers requests==2.32.3 # via @@ -288,59 +302,61 @@ requests==2.32.3 # opentelemetry-exporter-otlp-proto-http # outlines # transformers -rich==13.9.4 +rich==14.0.0 # via # text-generation-server (pyproject.toml) # typer -rpds-py==0.22.3 +rpds-py==0.24.0 # via # jsonschema # referencing -safetensors==0.4.5 +safetensors==0.5.3 # via # text-generation-server (pyproject.toml) # accelerate # peft # transformers -scipy==1.13.1 +scipy==1.15.3 # via text-generation-server (pyproject.toml) sentencepiece==0.2.0 # via text-generation-server (pyproject.toml) +setuptools==80.4.0 + # via triton shellingham==1.5.4 # via typer six==1.17.0 # via python-dateutil -sympy==1.13.1 +sympy==1.14.0 # via torch texttable==1.7.0 # via text-generation-server (pyproject.toml) -tokenizers==0.21.0 +tokenizers==0.21.1 # via # text-generation-server (pyproject.toml) # transformers -torch==2.6.0 +torch==2.7.0 # via # accelerate # compressed-tensors # outlines # peft -tqdm==4.66.5 +tqdm==4.67.1 # via # datasets # huggingface-hub # outlines # peft # transformers -transformers==4.49 +transformers==4.51.3 # via # text-generation-server (pyproject.toml) # compressed-tensors # peft -triton==3.2.0 +triton==3.3.0 # via torch -typer==0.15.1 +typer==0.15.3 # via text-generation-server (pyproject.toml) -typing-extensions==4.12.2 +typing-extensions==4.13.2 # via # huggingface-hub # opentelemetry-sdk @@ -350,18 +366,21 @@ typing-extensions==4.12.2 # referencing # torch # typer -tzdata==2025.1 + # typing-inspection +typing-inspection==0.4.0 + # via pydantic +tzdata==2025.2 # via pandas -urllib3==2.2.3 +urllib3==2.4.0 # via requests -wrapt==1.16.0 +wrapt==1.17.2 # via # deprecated # opentelemetry-instrumentation # opentelemetry-instrumentation-grpc xxhash==3.5.0 # via datasets -yarl==1.18.3 +yarl==1.20.0 # via aiohttp -zipp==3.20.2 +zipp==3.21.0 # via importlib-metadata diff --git a/server/uv.lock b/server/uv.lock index b4a95c13..7e6f194a 100644 --- a/server/uv.lock +++ b/server/uv.lock @@ -2,13 +2,17 @@ version = 1 revision = 1 requires-python = ">=3.9" resolution-markers = [ - "(python_full_version >= '3.12' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')", + "(python_full_version >= '3.12' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')", + "python_full_version >= '3.12' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version >= '3.12' and sys_platform != 'linux' and sys_platform != 'win32'", - "(python_full_version == '3.11.*' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform == 'win32')", + "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform == 'win32')", + "python_full_version == '3.11.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version == '3.11.*' and sys_platform != 'linux' and sys_platform != 'win32'", - "(python_full_version == '3.10.*' and sys_platform == 'linux') or (python_full_version == '3.10.*' and sys_platform == 'win32')", + "(python_full_version == '3.10.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.10.*' and sys_platform == 'win32')", + "python_full_version == '3.10.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version == '3.10.*' and sys_platform != 'linux' and sys_platform != 'win32'", - "(python_full_version < '3.10' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')", + "(python_full_version < '3.10' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')", + "python_full_version < '3.10' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version < '3.10' and sys_platform != 'linux' and sys_platform != 'win32'", ] @@ -24,8 +28,8 @@ dependencies = [ { name = "psutil" }, { name = "pyyaml" }, { name = "safetensors" }, - { name = "torch", version = "2.6.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, - { name = "torch", version = "2.6.0+cu124", source = { registry = "https://download.pytorch.org/whl/cu124" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "torch", version = "2.7.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, + { name = "torch", version = "2.7.0+cu128", source = { registry = "https://download.pytorch.org/whl/cu128" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/85/15/0fab0260ab4069e5224e637d2e400538bb27b0dfc36f17daf68db9770d78/accelerate-1.3.0.tar.gz", hash = "sha256:518631c0adb80bd3d42fb29e7e2dc2256bcd7c786b0ba9119bbaa08611b36d9c", size = 342758 } wheels = [ @@ -194,8 +198,8 @@ source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "numpy", version = "2.0.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" }, { name = "numpy", version = "2.2.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.10'" }, - { name = "torch", version = "2.6.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, - { name = "torch", version = "2.6.0+cu124", source = { registry = "https://download.pytorch.org/whl/cu124" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "torch", version = "2.7.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, + { name = "torch", version = "2.7.0+cu128", source = { registry = "https://download.pytorch.org/whl/cu128" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/db/9d/9382259196d7ad7f3550702390081224e673a705e75b5660ee377b592fc0/bitsandbytes-0.45.2-py3-none-manylinux_2_24_x86_64.whl", hash = "sha256:ba3a720187f518b172ebce4081049c682ae3fd8284947e22499b256ff99a2bc3", size = 69680042 }, @@ -321,8 +325,8 @@ version = "0.9.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "pydantic" }, - { name = "torch", version = "2.6.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, - { name = "torch", version = "2.6.0+cu124", source = { registry = "https://download.pytorch.org/whl/cu124" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "torch", version = "2.7.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, + { name = "torch", version = "2.7.0+cu128", source = { registry = "https://download.pytorch.org/whl/cu128" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, { name = "transformers" }, ] sdist = { url = "https://files.pythonhosted.org/packages/40/e0/d9529aae2d2425d214e5a50497df4532d3f9e21c8d2023037c701f8a37d3/compressed-tensors-0.9.1.tar.gz", hash = "sha256:3cf5cd637f0186c184dd5bbbbf941356b1225199b49c6a45bf0909d65907f686", size = 63060 } @@ -833,8 +837,8 @@ dependencies = [ { name = "huggingface-hub" }, { name = "packaging" }, { name = "tomli", marker = "python_full_version < '3.11'" }, - { name = "torch", version = "2.6.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, - { name = "torch", version = "2.6.0+cu124", source = { registry = "https://download.pytorch.org/whl/cu124" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "torch", version = "2.7.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, + { name = "torch", version = "2.7.0+cu128", source = { registry = "https://download.pytorch.org/whl/cu128" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/26/99/41af9dce502bb1682977fee1bc487a73fa8418cebbce16b8d27733947375/kernels-0.2.1.tar.gz", hash = "sha256:918942332819b28377b9d07070daddecfd8a5e7bab574dd3dc64a209ca6008b2", size = 9395 } @@ -1092,7 +1096,8 @@ name = "networkx" version = "3.2.1" source = { registry = "https://pypi.org/simple" } resolution-markers = [ - "(python_full_version < '3.10' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')", + "(python_full_version < '3.10' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')", + "python_full_version < '3.10' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version < '3.10' and sys_platform != 'linux' and sys_platform != 'win32'", ] sdist = { url = "https://files.pythonhosted.org/packages/c4/80/a84676339aaae2f1cfdf9f418701dd634aef9cc76f708ef55c36ff39c3ca/networkx-3.2.1.tar.gz", hash = "sha256:9f1bb5cf3409bf324e0a722c20bdb4c20ee39bf1c30ce8ae499c8502b0b5e0c6", size = 2073928 } @@ -1105,11 +1110,14 @@ name = "networkx" version = "3.4.2" source = { registry = "https://pypi.org/simple" } resolution-markers = [ - "(python_full_version >= '3.12' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')", + "(python_full_version >= '3.12' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')", + "python_full_version >= '3.12' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version >= '3.12' and sys_platform != 'linux' and sys_platform != 'win32'", - "(python_full_version == '3.11.*' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform == 'win32')", + "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform == 'win32')", + "python_full_version == '3.11.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version == '3.11.*' and sys_platform != 'linux' and sys_platform != 'win32'", - "(python_full_version == '3.10.*' and sys_platform == 'linux') or (python_full_version == '3.10.*' and sys_platform == 'win32')", + "(python_full_version == '3.10.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.10.*' and sys_platform == 'win32')", + "python_full_version == '3.10.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version == '3.10.*' and sys_platform != 'linux' and sys_platform != 'win32'", ] sdist = { url = "https://files.pythonhosted.org/packages/fd/1d/06475e1cd5264c0b870ea2cc6fdb3e37177c1e565c43f56ff17a10e3937f/networkx-3.4.2.tar.gz", hash = "sha256:307c3669428c5362aab27c8a1260aa8f47c4e91d3891f48be0141738d8d053e1", size = 2151368 } @@ -1122,7 +1130,8 @@ name = "numpy" version = "2.0.2" source = { registry = "https://pypi.org/simple" } resolution-markers = [ - "(python_full_version < '3.10' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')", + "(python_full_version < '3.10' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')", + "python_full_version < '3.10' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version < '3.10' and sys_platform != 'linux' and sys_platform != 'win32'", ] sdist = { url = "https://files.pythonhosted.org/packages/a9/75/10dd1f8116a8b796cb2c737b674e02d02e80454bda953fa7e65d8c12b016/numpy-2.0.2.tar.gz", hash = "sha256:883c987dee1880e2a864ab0dc9892292582510604156762362d9326444636e78", size = 18902015 } @@ -1178,11 +1187,14 @@ name = "numpy" version = "2.2.2" source = { registry = "https://pypi.org/simple" } resolution-markers = [ - "(python_full_version >= '3.12' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')", + "(python_full_version >= '3.12' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')", + "python_full_version >= '3.12' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version >= '3.12' and sys_platform != 'linux' and sys_platform != 'win32'", - "(python_full_version == '3.11.*' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform == 'win32')", + "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform == 'win32')", + "python_full_version == '3.11.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version == '3.11.*' and sys_platform != 'linux' and sys_platform != 'win32'", - "(python_full_version == '3.10.*' and sys_platform == 'linux') or (python_full_version == '3.10.*' and sys_platform == 'win32')", + "(python_full_version == '3.10.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.10.*' and sys_platform == 'win32')", + "python_full_version == '3.10.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version == '3.10.*' and sys_platform != 'linux' and sys_platform != 'win32'", ] sdist = { url = "https://files.pythonhosted.org/packages/ec/d0/c12ddfd3a02274be06ffc71f3efc6d0e457b0409c4481596881e748cb264/numpy-2.2.2.tar.gz", hash = "sha256:ed6906f61834d687738d25988ae117683705636936cc605be0bb208b23df4d8f", size = 20233295 } @@ -1245,120 +1257,128 @@ wheels = [ [[package]] name = "nvidia-cublas-cu12" -version = "12.4.5.8" +version = "12.8.3.14" source = { registry = "https://pypi.org/simple" } wheels = [ - { url = "https://files.pythonhosted.org/packages/ae/71/1c91302526c45ab494c23f61c7a84aa568b8c1f9d196efa5993957faf906/nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl", hash = "sha256:2fc8da60df463fdefa81e323eef2e36489e1c94335b5358bcb38360adf75ac9b", size = 363438805 }, + { url = "https://files.pythonhosted.org/packages/82/df/4b01f10069e23c641f116c62fc31e31e8dc361a153175d81561d15c8143b/nvidia_cublas_cu12-12.8.3.14-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:3f0e05e7293598cf61933258b73e66a160c27d59c4422670bf0b79348c04be44", size = 609620630 }, ] [[package]] name = "nvidia-cuda-cupti-cu12" -version = "12.4.127" +version = "12.8.57" source = { registry = "https://pypi.org/simple" } wheels = [ - { url = "https://files.pythonhosted.org/packages/67/42/f4f60238e8194a3106d06a058d494b18e006c10bb2b915655bd9f6ea4cb1/nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:9dec60f5ac126f7bb551c055072b69d85392b13311fcc1bcda2202d172df30fb", size = 13813957 }, + { url = "https://files.pythonhosted.org/packages/39/6f/3683ecf4e38931971946777d231c2df00dd5c1c4c2c914c42ad8f9f4dca6/nvidia_cuda_cupti_cu12-12.8.57-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:8e0b2eb847de260739bee4a3f66fac31378f4ff49538ff527a38a01a9a39f950", size = 10237547 }, ] [[package]] name = "nvidia-cuda-nvrtc-cu12" -version = "12.4.127" +version = "12.8.61" source = { registry = "https://pypi.org/simple" } wheels = [ - { url = "https://files.pythonhosted.org/packages/2c/14/91ae57cd4db3f9ef7aa99f4019cfa8d54cb4caa7e00975df6467e9725a9f/nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a178759ebb095827bd30ef56598ec182b85547f1508941a3d560eb7ea1fbf338", size = 24640306 }, + { url = "https://files.pythonhosted.org/packages/d4/22/32029d4583f7b19cfe75c84399cbcfd23f2aaf41c66fc8db4da460104fff/nvidia_cuda_nvrtc_cu12-12.8.61-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:a0fa9c2a21583105550ebd871bd76e2037205d56f33f128e69f6d2a55e0af9ed", size = 88024585 }, ] [[package]] name = "nvidia-cuda-runtime-cu12" -version = "12.4.127" +version = "12.8.57" source = { registry = "https://pypi.org/simple" } wheels = [ - { url = "https://files.pythonhosted.org/packages/ea/27/1795d86fe88ef397885f2e580ac37628ed058a92ed2c39dc8eac3adf0619/nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:64403288fa2136ee8e467cdc9c9427e0434110899d07c779f25b5c068934faa5", size = 883737 }, + { url = "https://files.pythonhosted.org/packages/16/f6/0e1ef31f4753a44084310ba1a7f0abaf977ccd810a604035abb43421c057/nvidia_cuda_runtime_cu12-12.8.57-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:75342e28567340b7428ce79a5d6bb6ca5ff9d07b69e7ce00d2c7b4dc23eff0be", size = 954762 }, ] [[package]] name = "nvidia-cudnn-cu12" -version = "9.1.0.70" +version = "9.7.1.26" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-cublas-cu12", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or sys_platform == 'win32'" }, ] wheels = [ - { url = "https://files.pythonhosted.org/packages/9f/fd/713452cd72343f682b1c7b9321e23829f00b842ceaedcda96e742ea0b0b3/nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl", hash = "sha256:165764f44ef8c61fcdfdfdbe769d687e06374059fbb388b6c89ecb0e28793a6f", size = 664752741 }, + { url = "https://files.pythonhosted.org/packages/25/dc/dc825c4b1c83b538e207e34f48f86063c88deaa35d46c651c7c181364ba2/nvidia_cudnn_cu12-9.7.1.26-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:6d011159a158f3cfc47bf851aea79e31bcff60d530b70ef70474c84cac484d07", size = 726851421 }, ] [[package]] name = "nvidia-cufft-cu12" -version = "11.2.1.3" +version = "11.3.3.41" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-nvjitlink-cu12", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or sys_platform == 'win32'" }, ] wheels = [ - { url = "https://files.pythonhosted.org/packages/27/94/3266821f65b92b3138631e9c8e7fe1fb513804ac934485a8d05776e1dd43/nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl", hash = "sha256:f083fc24912aa410be21fa16d157fed2055dab1cc4b6934a0e03cba69eb242b9", size = 211459117 }, + { url = "https://files.pythonhosted.org/packages/ac/26/b53c493c38dccb1f1a42e1a21dc12cba2a77fbe36c652f7726d9ec4aba28/nvidia_cufft_cu12-11.3.3.41-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:da650080ab79fcdf7a4b06aa1b460e99860646b176a43f6208099bdc17836b6a", size = 193118795 }, +] + +[[package]] +name = "nvidia-cufile-cu12" +version = "1.13.0.11" +source = { registry = "https://pypi.org/simple" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/e5/9c/1f3264d0a84c8a031487fb7f59780fc78fa6f1c97776233956780e3dc3ac/nvidia_cufile_cu12-1.13.0.11-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:483f434c541806936b98366f6d33caef5440572de8ddf38d453213729da3e7d4", size = 1197801 }, ] [[package]] name = "nvidia-curand-cu12" -version = "10.3.5.147" +version = "10.3.9.55" source = { registry = "https://pypi.org/simple" } wheels = [ - { url = "https://files.pythonhosted.org/packages/8a/6d/44ad094874c6f1b9c654f8ed939590bdc408349f137f9b98a3a23ccec411/nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a88f583d4e0bb643c49743469964103aa59f7f708d862c3ddb0fc07f851e3b8b", size = 56305206 }, + { url = "https://files.pythonhosted.org/packages/bd/fc/7be5d0082507269bb04ac07cc614c84b78749efb96e8cf4100a8a1178e98/nvidia_curand_cu12-10.3.9.55-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:8387d974240c91f6a60b761b83d4b2f9b938b7e0b9617bae0f0dafe4f5c36b86", size = 63618038 }, ] [[package]] name = "nvidia-cusolver-cu12" -version = "11.6.1.9" +version = "11.7.2.55" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-cublas-cu12", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, - { name = "nvidia-cusparse-cu12", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, - { name = "nvidia-nvjitlink-cu12", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or sys_platform == 'win32'" }, + { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or sys_platform == 'win32'" }, + { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or sys_platform == 'win32'" }, ] wheels = [ - { url = "https://files.pythonhosted.org/packages/3a/e1/5b9089a4b2a4790dfdea8b3a006052cfecff58139d5a4e34cb1a51df8d6f/nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl", hash = "sha256:19e33fa442bcfd085b3086c4ebf7e8debc07cfe01e11513cc6d332fd918ac260", size = 127936057 }, + { url = "https://files.pythonhosted.org/packages/c2/08/953675873a136d96bb12f93b49ba045d1107bc94d2551c52b12fa6c7dec3/nvidia_cusolver_cu12-11.7.2.55-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:4d1354102f1e922cee9db51920dba9e2559877cf6ff5ad03a00d853adafb191b", size = 260373342 }, ] [[package]] name = "nvidia-cusparse-cu12" -version = "12.3.1.170" +version = "12.5.7.53" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-nvjitlink-cu12", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or sys_platform == 'win32'" }, ] wheels = [ - { url = "https://files.pythonhosted.org/packages/db/f7/97a9ea26ed4bbbfc2d470994b8b4f338ef663be97b8f677519ac195e113d/nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl", hash = "sha256:ea4f11a2904e2a8dc4b1833cc1b5181cde564edd0d5cd33e3c168eff2d1863f1", size = 207454763 }, + { url = "https://files.pythonhosted.org/packages/c2/ab/31e8149c66213b846c082a3b41b1365b831f41191f9f40c6ddbc8a7d550e/nvidia_cusparse_cu12-12.5.7.53-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:3c1b61eb8c85257ea07e9354606b26397612627fdcd327bfd91ccf6155e7c86d", size = 292064180 }, ] [[package]] name = "nvidia-cusparselt-cu12" -version = "0.6.2" +version = "0.6.3" source = { registry = "https://pypi.org/simple" } wheels = [ - { url = "https://files.pythonhosted.org/packages/78/a8/bcbb63b53a4b1234feeafb65544ee55495e1bb37ec31b999b963cbccfd1d/nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_x86_64.whl", hash = "sha256:df2c24502fd76ebafe7457dbc4716b2fec071aabaed4fb7691a201cde03704d9", size = 150057751 }, + { url = "https://files.pythonhosted.org/packages/3b/9a/72ef35b399b0e183bc2e8f6f558036922d453c4d8237dab26c666a04244b/nvidia_cusparselt_cu12-0.6.3-py3-none-manylinux2014_x86_64.whl", hash = "sha256:e5c8a26c36445dd2e6812f1177978a24e2d37cacce7e090f297a688d1ec44f46", size = 156785796 }, ] [[package]] name = "nvidia-nccl-cu12" -version = "2.21.5" +version = "2.26.2" source = { registry = "https://pypi.org/simple" } wheels = [ - { url = "https://files.pythonhosted.org/packages/df/99/12cd266d6233f47d00daf3a72739872bdc10267d0383508b0b9c84a18bb6/nvidia_nccl_cu12-2.21.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:8579076d30a8c24988834445f8d633c697d42397e92ffc3f63fa26766d25e0a0", size = 188654414 }, + { url = "https://files.pythonhosted.org/packages/67/ca/f42388aed0fddd64ade7493dbba36e1f534d4e6fdbdd355c6a90030ae028/nvidia_nccl_cu12-2.26.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:694cf3879a206553cc9d7dbda76b13efaf610fdb70a50cba303de1b0d1530ac6", size = 201319755 }, ] [[package]] name = "nvidia-nvjitlink-cu12" -version = "12.4.127" +version = "12.8.61" source = { registry = "https://pypi.org/simple" } wheels = [ - { url = "https://files.pythonhosted.org/packages/ff/ff/847841bacfbefc97a00036e0fce5a0f086b640756dc38caea5e1bb002655/nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:06b3b9b25bf3f8af351d664978ca26a16d2c5127dbd53c0497e28d1fb9611d57", size = 21066810 }, + { url = "https://files.pythonhosted.org/packages/03/f8/9d85593582bd99b8d7c65634d2304780aefade049b2b94d96e44084be90b/nvidia_nvjitlink_cu12-12.8.61-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:45fd79f2ae20bd67e8bc411055939049873bfd8fac70ff13bd4865e0b9bdab17", size = 39243473 }, ] [[package]] name = "nvidia-nvtx-cu12" -version = "12.4.127" +version = "12.8.55" source = { registry = "https://pypi.org/simple" } wheels = [ - { url = "https://files.pythonhosted.org/packages/87/20/199b8713428322a2f22b722c62b8cc278cc53dffa9705d744484b5035ee9/nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:781e950d9b9f60d8241ccea575b32f5105a5baf4c2351cab5256a24869f12a1a", size = 99144 }, + { url = "https://files.pythonhosted.org/packages/8d/cd/0e8c51b2ae3a58f054f2e7fe91b82d201abfb30167f2431e9bd92d532f42/nvidia_nvtx_cu12-12.8.55-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:2dd0780f1a55c21d8e06a743de5bd95653de630decfff40621dbde78cc307102", size = 89896 }, ] [[package]] @@ -1525,8 +1545,8 @@ dependencies = [ { name = "pydantic" }, { name = "referencing" }, { name = "requests" }, - { name = "torch", version = "2.6.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, - { name = "torch", version = "2.6.0+cu124", source = { registry = "https://download.pytorch.org/whl/cu124" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "torch", version = "2.7.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, + { name = "torch", version = "2.7.0+cu128", source = { registry = "https://download.pytorch.org/whl/cu128" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, { name = "tqdm" }, { name = "typing-extensions" }, ] @@ -1649,8 +1669,8 @@ dependencies = [ { name = "psutil" }, { name = "pyyaml" }, { name = "safetensors" }, - { name = "torch", version = "2.6.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, - { name = "torch", version = "2.6.0+cu124", source = { registry = "https://download.pytorch.org/whl/cu124" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "torch", version = "2.7.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, + { name = "torch", version = "2.7.0+cu128", source = { registry = "https://download.pytorch.org/whl/cu128" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, { name = "tqdm" }, { name = "transformers" }, ] @@ -2418,7 +2438,8 @@ name = "scipy" version = "1.13.1" source = { registry = "https://pypi.org/simple" } resolution-markers = [ - "(python_full_version < '3.10' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')", + "(python_full_version < '3.10' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')", + "python_full_version < '3.10' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version < '3.10' and sys_platform != 'linux' and sys_platform != 'win32'", ] dependencies = [ @@ -2457,11 +2478,14 @@ name = "scipy" version = "1.15.1" source = { registry = "https://pypi.org/simple" } resolution-markers = [ - "(python_full_version >= '3.12' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')", + "(python_full_version >= '3.12' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')", + "python_full_version >= '3.12' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version >= '3.12' and sys_platform != 'linux' and sys_platform != 'win32'", - "(python_full_version == '3.11.*' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform == 'win32')", + "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform == 'win32')", + "python_full_version == '3.11.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version == '3.11.*' and sys_platform != 'linux' and sys_platform != 'win32'", - "(python_full_version == '3.10.*' and sys_platform == 'linux') or (python_full_version == '3.10.*' and sys_platform == 'win32')", + "(python_full_version == '3.10.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.10.*' and sys_platform == 'win32')", + "python_full_version == '3.10.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", "python_full_version == '3.10.*' and sys_platform != 'linux' and sys_platform != 'win32'", ] dependencies = [ @@ -2579,14 +2603,14 @@ wheels = [ [[package]] name = "sympy" -version = "1.13.1" +version = "1.14.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "mpmath" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/ca/99/5a5b6f19ff9f083671ddf7b9632028436167cd3d33e11015754e41b249a4/sympy-1.13.1.tar.gz", hash = "sha256:9cebf7e04ff162015ce31c9c6c9144daa34a93bd082f54fd8f12deca4f47515f", size = 7533040 } +sdist = { url = "https://files.pythonhosted.org/packages/83/d3/803453b36afefb7c2bb238361cd4ae6125a569b4db67cd9e79846ba2d68c/sympy-1.14.0.tar.gz", hash = "sha256:d3d3fe8df1e5a0b42f0e7bdf50541697dbe7d23746e894990c030e2b05e72517", size = 7793921 } wheels = [ - { url = "https://files.pythonhosted.org/packages/b2/fe/81695a1aa331a842b582453b605175f419fe8540355886031328089d840a/sympy-1.13.1-py3-none-any.whl", hash = "sha256:db36cdc64bf61b9b24578b6f7bab1ecdd2452cf008f34faa33776680c26d66f8", size = 6189177 }, + { url = "https://files.pythonhosted.org/packages/a2/09/77d55d46fd61b4a135c444fc97158ef34a095e5681d0a6c10b75bf356191/sympy-1.14.0-py3-none-any.whl", hash = "sha256:e091cc3e99d2141a0ba2847328f5479b05d94a6635cb96148ccb3f34671bd8f5", size = 6299353 }, ] [[package]] @@ -2594,6 +2618,7 @@ name = "text-generation-server" version = "2.0.5.dev0" source = { editable = "." } dependencies = [ + { name = "click" }, { name = "einops" }, { name = "grpc-interceptor" }, { name = "grpcio" }, @@ -2652,16 +2677,18 @@ quantize = [ { name = "texttable" }, ] torch = [ - { name = "torch", version = "2.6.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, - { name = "torch", version = "2.6.0+cu124", source = { registry = "https://download.pytorch.org/whl/cu124" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, - { name = "torchvision", version = "0.21.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, - { name = "torchvision", version = "0.21.0+cu124", source = { registry = "https://download.pytorch.org/whl/cu124" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "torch", version = "2.7.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, + { name = "torch", version = "2.7.0+cu128", source = { registry = "https://download.pytorch.org/whl/cu128" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "torchvision", version = "0.22.0", source = { registry = "https://download.pytorch.org/whl/cu128" }, marker = "platform_machine == 'aarch64' and sys_platform == 'linux'" }, + { name = "torchvision", version = "0.22.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, + { name = "torchvision", version = "0.22.0+cu128", source = { registry = "https://download.pytorch.org/whl/cu128" }, marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or sys_platform == 'win32'" }, ] [package.metadata] requires-dist = [ { name = "accelerate", marker = "extra == 'accelerate'", specifier = ">=1.2.1,<2" }, { name = "bitsandbytes", marker = "extra == 'bnb'", specifier = ">=0.45.0" }, + { name = "click", specifier = "<8.2.0" }, { name = "compressed-tensors", marker = "extra == 'compressed-tensors'", specifier = ">=0.9.0" }, { name = "datasets", marker = "extra == 'quantize'", specifier = ">=2.21,<3" }, { name = "einops", specifier = ">=0.8.0" }, @@ -2694,10 +2721,10 @@ requires-dist = [ { name = "sentencepiece", specifier = ">=0.2.0" }, { name = "texttable", marker = "extra == 'quantize'", specifier = ">=1.6.7,<2" }, { name = "tokenizers", specifier = ">=0.20.3" }, - { name = "torch", marker = "(sys_platform == 'linux' and extra == 'torch') or (sys_platform == 'win32' and extra == 'torch')", specifier = "==2.6.0", index = "https://download.pytorch.org/whl/cu124" }, - { name = "torch", marker = "sys_platform != 'linux' and sys_platform != 'win32' and extra == 'torch'", specifier = "==2.6.0" }, - { name = "torchvision", marker = "(sys_platform == 'linux' and extra == 'torch') or (sys_platform == 'win32' and extra == 'torch')", specifier = "==0.21.0", index = "https://download.pytorch.org/whl/cu124" }, - { name = "torchvision", marker = "sys_platform != 'linux' and sys_platform != 'win32' and extra == 'torch'", specifier = "==0.21.0" }, + { name = "torch", marker = "(sys_platform == 'linux' and extra == 'torch') or (sys_platform == 'win32' and extra == 'torch')", specifier = "==2.7.0", index = "https://download.pytorch.org/whl/cu128" }, + { name = "torch", marker = "sys_platform != 'linux' and sys_platform != 'win32' and extra == 'torch'", specifier = "==2.7.0" }, + { name = "torchvision", marker = "(sys_platform == 'linux' and extra == 'torch') or (sys_platform == 'win32' and extra == 'torch')", specifier = "==0.22.0", index = "https://download.pytorch.org/whl/cu128" }, + { name = "torchvision", marker = "sys_platform != 'linux' and sys_platform != 'win32' and extra == 'torch'", specifier = "==0.22.0" }, { name = "transformers", specifier = ">=4.51.0" }, { name = "typer", specifier = ">=0.15.1" }, ] @@ -2778,7 +2805,7 @@ wheels = [ [[package]] name = "torch" -version = "2.6.0" +version = "2.7.0" source = { registry = "https://pypi.org/simple" } resolution-markers = [ "python_full_version >= '3.12' and sys_platform != 'linux' and sys_platform != 'win32'", @@ -2797,22 +2824,27 @@ dependencies = [ { name = "typing-extensions", marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, ] wheels = [ - { url = "https://files.pythonhosted.org/packages/e5/16/ea1b7842413a7b8a5aaa5e99e8eaf3da3183cc3ab345ad025a07ff636301/torch-2.6.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:09e06f9949e1a0518c5b09fe95295bc9661f219d9ecb6f9893e5123e10696628", size = 66520221 }, - { url = "https://files.pythonhosted.org/packages/0b/fa/f33a4148c6fb46ca2a3f8de39c24d473822d5774d652b66ed9b1214da5f7/torch-2.6.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:94fc63b3b4bedd327af588696559f68c264440e2503cc9e6954019473d74ae21", size = 66530713 }, - { url = "https://files.pythonhosted.org/packages/81/b4/605ae4173aa37fb5aa14605d100ff31f4f5d49f617928c9f486bb3aaec08/torch-2.6.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:9a610afe216a85a8b9bc9f8365ed561535c93e804c2a317ef7fabcc5deda0989", size = 66532538 }, - { url = "https://files.pythonhosted.org/packages/88/8b/d60c0491ab63634763be1537ad488694d316ddc4a20eaadd639cedc53971/torch-2.6.0-cp313-none-macosx_11_0_arm64.whl", hash = "sha256:ff96f4038f8af9f7ec4231710ed4549da1bdebad95923953a25045dcf6fd87e2", size = 66536783 }, - { url = "https://files.pythonhosted.org/packages/b3/17/41f681b87290a1d2f1394f943e470f8b0b3c2987b7df8dc078d8831fce5b/torch-2.6.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:265f70de5fd45b864d924b64be1797f86e76c8e48a02c2a3a6fc7ec247d2226c", size = 66520446 }, + { url = "https://files.pythonhosted.org/packages/dc/0b/b2b83f30b8e84a51bf4f96aa3f5f65fdf7c31c591cc519310942339977e2/torch-2.7.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:34e0168ed6de99121612d72224e59b2a58a83dae64999990eada7260c5dd582d", size = 68559462 }, + { url = "https://files.pythonhosted.org/packages/aa/3f/85b56f7e2abcfa558c5fbf7b11eb02d78a4a63e6aeee2bbae3bb552abea5/torch-2.7.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:0a8d43caa342b9986101ec5feb5bbf1d86570b5caa01e9cb426378311258fdde", size = 68569377 }, + { url = "https://files.pythonhosted.org/packages/ee/8d/b2939e5254be932db1a34b2bd099070c509e8887e0c5a90c498a917e4032/torch-2.7.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:30b7688a87239a7de83f269333651d8e582afffce6f591fff08c046f7787296e", size = 68574294 }, + { url = "https://files.pythonhosted.org/packages/28/fd/74ba6fde80e2b9eef4237fe668ffae302c76f0e4221759949a632ca13afa/torch-2.7.0-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:edad98dddd82220465b106506bb91ee5ce32bd075cddbcf2b443dfaa2cbd83bf", size = 68856166 }, + { url = "https://files.pythonhosted.org/packages/90/48/7e6477cf40d48cc0a61fa0d41ee9582b9a316b12772fcac17bc1a40178e7/torch-2.7.0-cp313-none-macosx_11_0_arm64.whl", hash = "sha256:27f5007bdf45f7bb7af7f11d1828d5c2487e030690afb3d89a651fd7036a390e", size = 68575074 }, + { url = "https://files.pythonhosted.org/packages/85/11/571d6363d1aaee3033af46b40798a0238b24522e9b291b676446943cc8a9/torch-2.7.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:ccd7509141713997861b7a947ef0a717143cd7e9240addd168f38ba8fd23fd56", size = 68560465 }, ] [[package]] name = "torch" -version = "2.6.0+cu124" -source = { registry = "https://download.pytorch.org/whl/cu124" } +version = "2.7.0+cu128" +source = { registry = "https://download.pytorch.org/whl/cu128" } resolution-markers = [ - "(python_full_version >= '3.12' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')", - "(python_full_version == '3.11.*' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform == 'win32')", - "(python_full_version == '3.10.*' and sys_platform == 'linux') or (python_full_version == '3.10.*' and sys_platform == 'win32')", - "(python_full_version < '3.10' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')", + "(python_full_version >= '3.12' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')", + "python_full_version >= '3.12' and platform_machine == 'aarch64' and sys_platform == 'linux'", + "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform == 'win32')", + "python_full_version == '3.11.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", + "(python_full_version == '3.10.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.10.*' and sys_platform == 'win32')", + "python_full_version == '3.10.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", + "(python_full_version < '3.10' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')", + "python_full_version < '3.10' and platform_machine == 'aarch64' and sys_platform == 'linux'", ] dependencies = [ { name = "filelock", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, @@ -2826,6 +2858,7 @@ dependencies = [ { name = "nvidia-cuda-runtime-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" }, { name = "nvidia-cudnn-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" }, { name = "nvidia-cufft-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" }, + { name = "nvidia-cufile-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" }, { name = "nvidia-curand-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" }, { name = "nvidia-cusolver-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" }, { name = "nvidia-cusparse-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" }, @@ -2835,26 +2868,58 @@ dependencies = [ { name = "nvidia-nvtx-cu12", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" }, { name = "setuptools", marker = "(python_full_version >= '3.12' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')" }, { name = "sympy", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, - { name = "triton", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" }, + { name = "triton", marker = "sys_platform == 'linux'" }, { name = "typing-extensions", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, ] wheels = [ - { url = "https://download.pytorch.org/whl/cu124/torch-2.6.0%2Bcu124-cp310-cp310-linux_x86_64.whl", hash = "sha256:7f2ba7f7c0459320a521696f6b5bccc187f59890b23c9dfb6c49b0b87c6bfc97" }, - { url = "https://download.pytorch.org/whl/cu124/torch-2.6.0%2Bcu124-cp310-cp310-win_amd64.whl", hash = "sha256:7cc45c5b39d74875cfafe908b7f55c544147cc16b01e795feb2fe766583efe78" }, - { url = "https://download.pytorch.org/whl/cu124/torch-2.6.0%2Bcu124-cp311-cp311-linux_x86_64.whl", hash = "sha256:d4c3e9a8d31a7c0fcbb9da17c31a1917e1fac26c566a4cfbd8c9568ad7cade79" }, - { url = "https://download.pytorch.org/whl/cu124/torch-2.6.0%2Bcu124-cp311-cp311-win_amd64.whl", hash = "sha256:6a1fb2714e9323f11edb6e8abf7aad5f79e45ad25c081cde87681a18d99c29eb" }, - { url = "https://download.pytorch.org/whl/cu124/torch-2.6.0%2Bcu124-cp312-cp312-linux_x86_64.whl", hash = "sha256:a393b506844035c0dac2f30ea8478c343b8e95a429f06f3b3cadfc7f53adb597" }, - { url = "https://download.pytorch.org/whl/cu124/torch-2.6.0%2Bcu124-cp312-cp312-win_amd64.whl", hash = "sha256:3313061c1fec4c7310cf47944e84513dcd27b6173b72a349bb7ca68d0ee6e9c0" }, - { url = "https://download.pytorch.org/whl/cu124/torch-2.6.0%2Bcu124-cp313-cp313-linux_x86_64.whl", hash = "sha256:0f3bc53c988ce9568cd876a2a5316761e84a8704135ec8068f5f81b4417979cb" }, - { url = "https://download.pytorch.org/whl/cu124/torch-2.6.0%2Bcu124-cp313-cp313-win_amd64.whl", hash = "sha256:519330eef09534acad8110b6f423d2fe58c1d8e9ada999ed077a637a0021f908" }, - { url = "https://download.pytorch.org/whl/cu124/torch-2.6.0%2Bcu124-cp313-cp313t-linux_x86_64.whl", hash = "sha256:35cba404c0d742406cdcba1609085874bc60facdfbc50e910c47a92405fef44c" }, - { url = "https://download.pytorch.org/whl/cu124/torch-2.6.0%2Bcu124-cp39-cp39-linux_x86_64.whl", hash = "sha256:e661267cd0242462ab100bdd67f651988aa9f67eb31609d6909afcac891df612" }, - { url = "https://download.pytorch.org/whl/cu124/torch-2.6.0%2Bcu124-cp39-cp39-win_amd64.whl", hash = "sha256:c2eb62b99161d87be486c88fd82441274cc892bce8c48dbc28c055cb147732ce" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp310-cp310-manylinux_2_28_aarch64.whl" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:ac1849553ee673dfafb44c610c60cb60a2890f0e117f43599a526cf777eb8b8c" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp310-cp310-win_amd64.whl", hash = "sha256:c52c4b869742f00b12cb34521d1381be6119fa46244791704b00cc4a3cb06850" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp311-cp311-manylinux_2_28_aarch64.whl" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:c4bbc0b4be60319ba1cefc90be9557b317f0b3c261eeceb96ca6e0343eec56bf" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp311-cp311-win_amd64.whl", hash = "sha256:bf88f647d76d79da9556ca55df49e45aff1d66c12797886364343179dd09a36c" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp312-cp312-manylinux_2_28_aarch64.whl" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:7c0f08d1c44a02abad389373dddfce75904b969a410be2f4e5109483dd3dc0ce" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp312-cp312-win_amd64.whl", hash = "sha256:1704e5dd66c9221e4e8b6ae2d80cbf54e129571e643f5fa9ca78cc6d2096403a" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313-manylinux_2_28_aarch64.whl" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:d2f69f909da5dc52113ec66a851d62079f3d52c83184cf64beebdf12ca2f705c" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313-win_amd64.whl", hash = "sha256:58c749f52ddc9098155c77d6c74153bb13d8978fd6e1063b5d7b41d4644f5af5" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313t-manylinux_2_28_aarch64.whl" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:78e13c26c38ae92d6841cf9ce760d7e9d52bca3e3183de371812e84274b054dc" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp313-cp313t-win_amd64.whl", hash = "sha256:3559e98be824c2b12ab807319cd61c6174d73a524c9961317de8e8a44133c5c5" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp39-cp39-manylinux_2_28_aarch64.whl" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:f446f97b20cb070747b103fb640df941b88cb68c8d3b01538287d05d56a7e874" }, + { url = "https://download.pytorch.org/whl/cu128/torch-2.7.0%2Bcu128-cp39-cp39-win_amd64.whl", hash = "sha256:8614a167d6a163273fb130f586802f3243479862b53ee2843941c10cc5761da6" }, ] [[package]] name = "torchvision" -version = "0.21.0" +version = "0.22.0" +source = { registry = "https://download.pytorch.org/whl/cu128" } +resolution-markers = [ + "python_full_version >= '3.12' and platform_machine == 'aarch64' and sys_platform == 'linux'", + "python_full_version == '3.11.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", + "python_full_version == '3.10.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", + "python_full_version < '3.10' and platform_machine == 'aarch64' and sys_platform == 'linux'", +] +dependencies = [ + { name = "numpy", version = "2.0.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10' and platform_machine == 'aarch64' and sys_platform == 'linux'" }, + { name = "numpy", version = "2.2.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.10' and platform_machine == 'aarch64' and sys_platform == 'linux'" }, + { name = "pillow", marker = "platform_machine == 'aarch64' and sys_platform == 'linux'" }, + { name = "torch", version = "2.7.0+cu128", source = { registry = "https://download.pytorch.org/whl/cu128" }, marker = "platform_machine == 'aarch64' and sys_platform == 'linux'" }, +] +wheels = [ + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:566224d7b4f00bc6366bed1d62f834ca80f8e57fe41e10e4a5636bfa3ffb984e" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:6be714bcdd8849549571f6acfaa2dfa9e00676f042bda517432745fb116f7904" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:6e9752b48c1cdd7f6428bcd30c3d198b30ecea348d16afb651f95035e5252506" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:e4d4d5a14225875d9bf8c5221d43d8be97786adc498659493799bdeff52c54cf" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:e50ff5bbae11f57fd3af8e6f2185c136f32e8b94324613428228dd27eba6a4f6" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:7a398fad02f4ac6b7d18bea9a08dc14163ffc5a368618f29ceb0e53dfa91f69e" }, +] + +[[package]] +name = "torchvision" +version = "0.22.0" source = { registry = "https://pypi.org/simple" } resolution-markers = [ "python_full_version >= '3.12' and sys_platform != 'linux' and sys_platform != 'win32'", @@ -2866,43 +2931,46 @@ dependencies = [ { name = "numpy", version = "2.0.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10' and sys_platform != 'linux' and sys_platform != 'win32'" }, { name = "numpy", version = "2.2.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.10' and sys_platform != 'linux' and sys_platform != 'win32'" }, { name = "pillow", marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, - { name = "torch", version = "2.6.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, + { name = "torch", version = "2.7.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux' and sys_platform != 'win32'" }, ] wheels = [ - { url = "https://files.pythonhosted.org/packages/8e/0d/143bd264876fad17c82096b6c2d433f1ac9b29cdc69ee45023096976ee3d/torchvision-0.21.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:044ea420b8c6c3162a234cada8e2025b9076fa82504758cd11ec5d0f8cd9fa37", size = 1784140 }, - { url = "https://files.pythonhosted.org/packages/29/88/00c69db213ee2443ada8886ec60789b227e06bb869d85ee324578221a7f7/torchvision-0.21.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:110d115333524d60e9e474d53c7d20f096dbd8a080232f88dddb90566f90064c", size = 1784141 }, - { url = "https://files.pythonhosted.org/packages/6e/1b/28f527b22d5e8800184d0bc847f801ae92c7573a8c15979d92b7091c0751/torchvision-0.21.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:97a5814a93c793aaf0179cfc7f916024f4b63218929aee977b645633d074a49f", size = 1784140 }, - { url = "https://files.pythonhosted.org/packages/f9/56/47d456b61c3bbce7bed4af3925c83d405bb87468e659fd3cf3d9840c3b51/torchvision-0.21.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:659b76c86757cb2ee4ca2db245e0740cfc3081fef46f0f1064d11adb4a8cee31", size = 1784141 }, - { url = "https://files.pythonhosted.org/packages/49/d5/d18c5d89cbe32015b033f1fa06918c7cdd5c0af0c03e55d72a3cc2d768f8/torchvision-0.21.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5c22caeaae8b3c36d93459f1a5294e6f43306cff856ed243189a229331a404b4", size = 1784154 }, + { url = "https://files.pythonhosted.org/packages/eb/03/a514766f068b088180f273913e539d08e830be3ae46ef8577ea62584a27c/torchvision-0.22.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:72256f1d7ff510b16c9fb4dd488584d0693f40c792f286a9620674438a81ccca", size = 1947829 }, + { url = "https://files.pythonhosted.org/packages/b1/43/28bc858b022f6337326d75f4027d2073aad5432328f01ee1236d847f1b82/torchvision-0.22.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:191ea28321fc262d8aa1a7fe79c41ff2848864bf382f9f6ea45c41dde8313792", size = 1947828 }, + { url = "https://files.pythonhosted.org/packages/cb/ea/887d1d61cf4431a46280972de665f350af1898ce5006cd046326e5d0a2f2/torchvision-0.22.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:31c3165418fe21c3d81fe3459e51077c2f948801b8933ed18169f54652796a0f", size = 1947826 }, + { url = "https://files.pythonhosted.org/packages/e1/2a/9b34685599dcb341d12fc2730055155623db7a619d2415a8d31f17050952/torchvision-0.22.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:ece17995857dd328485c9c027c0b20ffc52db232e30c84ff6c95ab77201112c5", size = 1947823 }, + { url = "https://files.pythonhosted.org/packages/6f/a7/f43e9c8d13118b4ffbaebea664c9338ab20fa115a908125afd2238ff16e7/torchvision-0.22.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:cdc96daa4658b47ce9384154c86ed1e70cba9d972a19f5de6e33f8f94a626790", size = 2137621 }, + { url = "https://files.pythonhosted.org/packages/3a/6e/eb662050a22a75a85b3b5e5f33dddfdc487c10ffcd20b82a8c2a4a6cd56c/torchvision-0.22.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:2ef38a397f1b9cf62846fb20659cb99101f9d361de8c45d79284ee45c6f40d50", size = 1947880 }, ] [[package]] name = "torchvision" -version = "0.21.0+cu124" -source = { registry = "https://download.pytorch.org/whl/cu124" } +version = "0.22.0+cu128" +source = { registry = "https://download.pytorch.org/whl/cu128" } resolution-markers = [ - "(python_full_version >= '3.12' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')", - "(python_full_version == '3.11.*' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform == 'win32')", - "(python_full_version == '3.10.*' and sys_platform == 'linux') or (python_full_version == '3.10.*' and sys_platform == 'win32')", - "(python_full_version < '3.10' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')", + "(python_full_version >= '3.12' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12' and sys_platform == 'win32')", + "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform == 'win32')", + "(python_full_version == '3.10.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.10.*' and sys_platform == 'win32')", + "(python_full_version < '3.10' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')", ] dependencies = [ - { name = "numpy", version = "2.0.2", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version < '3.10' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')" }, - { name = "numpy", version = "2.2.2", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version >= '3.10' and sys_platform == 'linux') or (python_full_version >= '3.10' and sys_platform == 'win32')" }, - { name = "pillow", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, - { name = "torch", version = "2.6.0+cu124", source = { registry = "https://download.pytorch.org/whl/cu124" }, marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, + { name = "numpy", version = "2.0.2", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version < '3.10' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.10' and sys_platform == 'win32')" }, + { name = "numpy", version = "2.2.2", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version >= '3.10' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.10' and sys_platform == 'win32')" }, + { name = "pillow", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or sys_platform == 'win32'" }, + { name = "torch", version = "2.7.0+cu128", source = { registry = "https://download.pytorch.org/whl/cu128" }, marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or sys_platform == 'win32'" }, ] wheels = [ - { url = "https://download.pytorch.org/whl/cu124/torchvision-0.21.0%2Bcu124-cp310-cp310-linux_x86_64.whl", hash = "sha256:3d3e74018eaa7837c73e3764dad3b7792b7544401c25a42977e9744303731bd3" }, - { url = "https://download.pytorch.org/whl/cu124/torchvision-0.21.0%2Bcu124-cp310-cp310-win_amd64.whl", hash = "sha256:0c6aefb70ab2b312065240c804e459ac7b0e449867afd469b38d2fd47f9391a7" }, - { url = "https://download.pytorch.org/whl/cu124/torchvision-0.21.0%2Bcu124-cp311-cp311-linux_x86_64.whl", hash = "sha256:137376805aca5ba57bd2c7a3ecb8569df961dbe82b128aac9b3b0a7125ef9385" }, - { url = "https://download.pytorch.org/whl/cu124/torchvision-0.21.0%2Bcu124-cp311-cp311-win_amd64.whl", hash = "sha256:000a013584ad2304ab30496318145f284ac364622addb5ee3a5abd2769ba146f" }, - { url = "https://download.pytorch.org/whl/cu124/torchvision-0.21.0%2Bcu124-cp312-cp312-linux_x86_64.whl", hash = "sha256:efb53ea0af7bf09b7b53e2a18b9be6d245f7d46a90b51d5cf97f37e9b929a991" }, - { url = "https://download.pytorch.org/whl/cu124/torchvision-0.21.0%2Bcu124-cp312-cp312-win_amd64.whl", hash = "sha256:ec63c2ee792757492da40590e34b14f2fceda29050558c215f0c1f3b08149c0f" }, - { url = "https://download.pytorch.org/whl/cu124/torchvision-0.21.0%2Bcu124-cp313-cp313-linux_x86_64.whl", hash = "sha256:4b70acf3b4b96a0ceb1374116626c9bef9e8be016b57b1284e482260ca1896d6" }, - { url = "https://download.pytorch.org/whl/cu124/torchvision-0.21.0%2Bcu124-cp313-cp313-win_amd64.whl", hash = "sha256:8fcf55321b206de70ff8e01c884fa42e57a60b1cb749341b96e0f22c8a7c9ec7" }, - { url = "https://download.pytorch.org/whl/cu124/torchvision-0.21.0%2Bcu124-cp39-cp39-linux_x86_64.whl", hash = "sha256:6afb21a22f5497e08ea4dbd4544472330d8249bf09dafd239302552cad6906b2" }, - { url = "https://download.pytorch.org/whl/cu124/torchvision-0.21.0%2Bcu124-cp39-cp39-win_amd64.whl", hash = "sha256:579b6a7fffc34a860c57a7131221ef125831f5961431f8da15760ab1ef752d44" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0%2Bcu128-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:59df5a550113a80ce523047066eaaedb168c69482da88c3ab246716ab45ba092" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0%2Bcu128-cp310-cp310-win_amd64.whl", hash = "sha256:cdd90b768b01b0d638cb06a6c211b550b275c0c207b5210b7cbb5cea8dde11db" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0%2Bcu128-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:f3ac527d58b4c2043eb8d9e29fc56cd1751f36f2aaa6dc75e34ec54c951bcb9c" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0%2Bcu128-cp311-cp311-win_amd64.whl", hash = "sha256:f5dae1307c34813425c0b753530c035e1cc72af0bded395d1ba64dcb2872889f" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0%2Bcu128-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:06c101f40e1ff94869be14487c91fd5352e376f202fdeafb8f53c58cee2fbeb5" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0%2Bcu128-cp312-cp312-win_amd64.whl", hash = "sha256:a87393c86649b7e56b4bf859fe95922ee6ec1c1f3b430246fb1a5b51f8aee37a" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0%2Bcu128-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:ee4fa6d4052d9ae25c1233289947fbfa4b88d23710254ab1772b108c1fc5fb4d" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0%2Bcu128-cp313-cp313-win_amd64.whl", hash = "sha256:17d50ffb1df6320da16b85395f1078bf369250ea144f3bb405088aca3d5f030f" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0%2Bcu128-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:209c29d78cf2003cf4e22c9b651790f57171334998ee3125594d130526aeaa50" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0%2Bcu128-cp313-cp313t-win_amd64.whl", hash = "sha256:03b454b867f7a0aa9861a463042141448c4f15bec784def19eed39a57fac217b" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0%2Bcu128-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:c92a353ff82db3312644b5b26d410b586b72969b535948d584c247569f75605c" }, + { url = "https://download.pytorch.org/whl/cu128/torchvision-0.22.0%2Bcu128-cp39-cp39-win_amd64.whl", hash = "sha256:90a0dacad36b1ea8de912af8583cbe780b4a1bdf9cb85870fe548fdec212ab31" }, ] [[package]] @@ -2941,19 +3009,23 @@ wheels = [ [[package]] name = "triton" -version = "3.2.0" +version = "3.3.0" source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "setuptools", marker = "sys_platform == 'linux' or sys_platform == 'win32'" }, +] wheels = [ - { url = "https://files.pythonhosted.org/packages/01/65/3ffa90e158a2c82f0716eee8d26a725d241549b7d7aaf7e4f44ac03ebd89/triton-3.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b3e54983cd51875855da7c68ec05c05cf8bb08df361b1d5b69e05e40b0c9bd62", size = 253090354 }, - { url = "https://files.pythonhosted.org/packages/a7/2e/757d2280d4fefe7d33af7615124e7e298ae7b8e3bc4446cdb8e88b0f9bab/triton-3.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8009a1fb093ee8546495e96731336a33fb8856a38e45bb4ab6affd6dbc3ba220", size = 253157636 }, - { url = "https://files.pythonhosted.org/packages/06/00/59500052cb1cf8cf5316be93598946bc451f14072c6ff256904428eaf03c/triton-3.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d9b215efc1c26fa7eefb9a157915c92d52e000d2bf83e5f69704047e63f125c", size = 253159365 }, - { url = "https://files.pythonhosted.org/packages/c7/30/37a3384d1e2e9320331baca41e835e90a3767303642c7a80d4510152cbcf/triton-3.2.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e5dfa23ba84541d7c0a531dfce76d8bcd19159d50a4a8b14ad01e91734a5c1b0", size = 253154278 }, - { url = "https://files.pythonhosted.org/packages/bc/74/9f12bdedeb110242d8bb1bd621f6605e753ee0cbf73cf7f3a62b8173f190/triton-3.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:30ceed0eff2c4a73b14eb63e052992f44bbdf175f3fad21e1ac8097a772de7ee", size = 253057866 }, + { url = "https://files.pythonhosted.org/packages/76/04/d54d3a6d077c646624dc9461b0059e23fd5d30e0dbe67471e3654aec81f9/triton-3.3.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fad99beafc860501d7fcc1fb7045d9496cbe2c882b1674640304949165a916e7", size = 156441993 }, + { url = "https://files.pythonhosted.org/packages/3c/c5/4874a81131cc9e934d88377fbc9d24319ae1fb540f3333b4e9c696ebc607/triton-3.3.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3161a2bf073d6b22c4e2f33f951f3e5e3001462b2570e6df9cd57565bdec2984", size = 156528461 }, + { url = "https://files.pythonhosted.org/packages/11/53/ce18470914ab6cfbec9384ee565d23c4d1c55f0548160b1c7b33000b11fd/triton-3.3.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b68c778f6c4218403a6bd01be7484f6dc9e20fe2083d22dd8aef33e3b87a10a3", size = 156504509 }, + { url = "https://files.pythonhosted.org/packages/7d/74/4bf2702b65e93accaa20397b74da46fb7a0356452c1bb94dbabaf0582930/triton-3.3.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:47bc87ad66fa4ef17968299acacecaab71ce40a238890acc6ad197c3abe2b8f1", size = 156516468 }, + { url = "https://files.pythonhosted.org/packages/0a/93/f28a696fa750b9b608baa236f8225dd3290e5aff27433b06143adc025961/triton-3.3.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ce4700fc14032af1e049005ae94ba908e71cd6c2df682239aed08e49bc71b742", size = 156580729 }, + { url = "https://files.pythonhosted.org/packages/f0/9c/315d25590fc309e2d28bb67953526238fac5d54548a16ceca992c76441bc/triton-3.3.0-cp39-cp39-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1f41403bfa0cbb3e24fd958ca7fee04e9681e55e539296db9aca30c42acae693", size = 156439372 }, ] [[package]] name = "typer" -version = "0.15.1" +version = "0.15.3" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "click" }, @@ -2961,9 +3033,9 @@ dependencies = [ { name = "shellingham" }, { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/cb/ce/dca7b219718afd37a0068f4f2530a727c2b74a8b6e8e0c0080a4c0de4fcd/typer-0.15.1.tar.gz", hash = "sha256:a0588c0a7fa68a1978a069818657778f86abe6ff5ea6abf472f940a08bfe4f0a", size = 99789 } +sdist = { url = "https://files.pythonhosted.org/packages/98/1a/5f36851f439884bcfe8539f6a20ff7516e7b60f319bbaf69a90dc35cc2eb/typer-0.15.3.tar.gz", hash = "sha256:818873625d0569653438316567861899f7e9972f2e6e0c16dab608345ced713c", size = 101641 } wheels = [ - { url = "https://files.pythonhosted.org/packages/d0/cc/0a838ba5ca64dc832aa43f727bd586309846b0ffb2ce52422543e6075e8a/typer-0.15.1-py3-none-any.whl", hash = "sha256:7994fb7b8155b64d3402518560648446072864beefd44aa2dc36972a5972e847", size = 44908 }, + { url = "https://files.pythonhosted.org/packages/48/20/9d953de6f4367163d23ec823200eb3ecb0050a2609691e512c8b95827a9b/typer-0.15.3-py3-none-any.whl", hash = "sha256:c86a65ad77ca531f03de08d1b9cb67cd09ad02ddddf4b34745b5008f43b239bd", size = 45253 }, ] [[package]]