From e9b200369c49fed90cbdcd24f89077ba74859c48 Mon Sep 17 00:00:00 2001 From: OlivierDehaene Date: Wed, 28 Feb 2024 16:12:14 +0100 Subject: [PATCH] v1.4.3 (#1609) --- Cargo.lock | 12 ++++++------ Cargo.toml | 2 +- docs/openapi.json | 2 +- docs/source/_toctree.yml | 2 -- docs/source/conceptual/guidance.md | 4 ++-- .../test_flash_llama_grammar_no_tools.json | 2 +- .../test_flash_llama_grammar_tools.json | 2 +- .../test_flash_llama_grammar_tools_auto.json | 2 +- .../test_flash_llama_grammar_tools_choice.json | 2 +- .../test_flash_llama_grammar_tools_stream.json | 2 +- integration-tests/pyproject.toml | 2 +- server/pyproject.toml | 2 +- 12 files changed, 17 insertions(+), 19 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 2878f370..ce423e52 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -2961,7 +2961,7 @@ dependencies = [ [[package]] name = "text-generation-benchmark" -version = "1.4.2" +version = "1.4.3" dependencies = [ "average", "clap", @@ -2982,7 +2982,7 @@ dependencies = [ [[package]] name = "text-generation-client" -version = "1.4.2" +version = "1.4.3" dependencies = [ "futures", "grpc-metadata", @@ -2999,7 +2999,7 @@ dependencies = [ [[package]] name = "text-generation-launcher" -version = "1.4.2" +version = "1.4.3" dependencies = [ "clap", "ctrlc", @@ -3015,7 +3015,7 @@ dependencies = [ [[package]] name = "text-generation-router" -version = "1.4.2" +version = "1.4.3" dependencies = [ "async-stream", "axum", @@ -3860,9 +3860,9 @@ checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6" [[package]] name = "winapi-util" -version = "0.1.7" +version = "0.1.8" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "134306a13c5647ad6453e8deaec55d3a44d6021970129e6188735e74bf546697" +checksum = "4d4cc384e1e73b93bafa6fb4f1df8c41695c8a91cf9c4c64358067d15a7b6c6b" dependencies = [ "windows-sys 0.52.0", ] diff --git a/Cargo.toml b/Cargo.toml index 02acaf5c..820eb0aa 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -9,7 +9,7 @@ members = [ resolver = "2" [workspace.package] -version = "1.4.2" +version = "1.4.3" edition = "2021" authors = ["Olivier Dehaene"] homepage = "https://github.com/huggingface/text-generation-inference" diff --git a/docs/openapi.json b/docs/openapi.json index f8e52a8d..e5ffba5e 100644 --- a/docs/openapi.json +++ b/docs/openapi.json @@ -10,7 +10,7 @@ "name": "Apache 2.0", "url": "https://www.apache.org/licenses/LICENSE-2.0" }, - "version": "1.4.2" + "version": "1.4.3" }, "paths": { "/": { diff --git a/docs/source/_toctree.yml b/docs/source/_toctree.yml index 73c88ccc..ad4f29f6 100644 --- a/docs/source/_toctree.yml +++ b/docs/source/_toctree.yml @@ -9,8 +9,6 @@ title: Supported Models and Hardware - local: messages_api title: Messages API - - local: guidance - title: Guidance title: Getting started - sections: - local: basic_tutorials/consuming_tgi diff --git a/docs/source/conceptual/guidance.md b/docs/source/conceptual/guidance.md index 8b9ba094..e3e80f22 100644 --- a/docs/source/conceptual/guidance.md +++ b/docs/source/conceptual/guidance.md @@ -262,7 +262,7 @@ curl localhost:3000/v1/chat/completions \ ], "tool_choice": "get_current_weather" }' -// {"id":"","object":"text_completion","created":1709051640,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.2-native","choices":[{"index":0,"message":{"role":"assistant","tool_calls":{"id":0,"type":"function","function":{"description":null,"name":"tools","parameters":{"format":"celsius","location":"New York"}}}},"logprobs":null,"finish_reason":"eos_token"}],"usage":{"prompt_tokens":157,"completion_tokens":19,"total_tokens":176}} +// {"id":"","object":"text_completion","created":1709051640,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-native","choices":[{"index":0,"message":{"role":"assistant","tool_calls":{"id":0,"type":"function","function":{"description":null,"name":"tools","parameters":{"format":"celsius","location":"New York"}}}},"logprobs":null,"finish_reason":"eos_token"}],"usage":{"prompt_tokens":157,"completion_tokens":19,"total_tokens":176}} ```
@@ -362,7 +362,7 @@ if __name__ == "__main__": import asyncio asyncio.run(main()) -# {"id":"","object":"text_completion","created":1709051942,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.2-native","choices":[{"index":0,"message":{"role":"assistant","tool_calls":{"id":0,"type":"function","function":{"description":null,"name":"tools","parameters":{"format":"celsius","location":"New York"}}}},"logprobs":null,"finish_reason":"eos_token"}],"usage":{"prompt_tokens":157,"completion_tokens":20,"total_tokens":177}} +# {"id":"","object":"text_completion","created":1709051942,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-native","choices":[{"index":0,"message":{"role":"assistant","tool_calls":{"id":0,"type":"function","function":{"description":null,"name":"tools","parameters":{"format":"celsius","location":"New York"}}}},"logprobs":null,"finish_reason":"eos_token"}],"usage":{"prompt_tokens":157,"completion_tokens":20,"total_tokens":177}} ``` diff --git a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_no_tools.json b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_no_tools.json index 3c4b4aea..c2cde431 100644 --- a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_no_tools.json +++ b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_no_tools.json @@ -17,7 +17,7 @@ "id": "", "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "object": "text_completion", - "system_fingerprint": "1.4.2-native", + "system_fingerprint": "1.4.3-native", "usage": { "completion_tokens": 100, "prompt_tokens": 60, diff --git a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools.json b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools.json index 9b9e33c6..7a6c010a 100644 --- a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools.json +++ b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools.json @@ -29,7 +29,7 @@ "id": "", "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "object": "text_completion", - "system_fingerprint": "1.4.2-native", + "system_fingerprint": "1.4.3-native", "usage": { "completion_tokens": 29, "prompt_tokens": 316, diff --git a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_auto.json b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_auto.json index de32c970..c5561e75 100644 --- a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_auto.json +++ b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_auto.json @@ -29,7 +29,7 @@ "id": "", "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "object": "text_completion", - "system_fingerprint": "1.4.2-native", + "system_fingerprint": "1.4.3-native", "usage": { "completion_tokens": 29, "prompt_tokens": 316, diff --git a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_choice.json b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_choice.json index 3551e205..e03a5511 100644 --- a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_choice.json +++ b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_choice.json @@ -28,7 +28,7 @@ "id": "", "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "object": "text_completion", - "system_fingerprint": "1.4.2-native", + "system_fingerprint": "1.4.3-native", "usage": { "completion_tokens": 21, "prompt_tokens": 187, diff --git a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_stream.json b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_stream.json index c367cc6f..ceec31d9 100644 --- a/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_stream.json +++ b/integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_stream.json @@ -23,5 +23,5 @@ "id": "", "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "object": "text_completion", - "system_fingerprint": "1.4.2-native" + "system_fingerprint": "1.4.3-native" } diff --git a/integration-tests/pyproject.toml b/integration-tests/pyproject.toml index b0b4a07c..815e54fa 100644 --- a/integration-tests/pyproject.toml +++ b/integration-tests/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "text-generation-integration-tests" -version = "1.4.2" +version = "1.4.3" description = "Text Generation Inference integration tests" authors = ["Nicolas Patry "] diff --git a/server/pyproject.toml b/server/pyproject.toml index 0263942a..9abefa43 100644 --- a/server/pyproject.toml +++ b/server/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "text-generation-server" -version = "1.4.2" +version = "1.4.3" description = "Text Generation Inference Python gRPC Server" authors = ["Olivier Dehaene "]