huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-06-19 15:52:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Lock on python 3.11

Browse Source
This commit is contained in:
Nicolas Patry 2025-02-05 12:28:19 +01:00
parent a1c78adc19
commit 76c458a8a2
No known key found for this signature in database
GPG Key ID: D2920555C90F704C
6 changed files with 223 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
server/Makefile
View File

@ -37,6 +37,6 @@ install-cuda: install-server install-flash-attention-v2-cuda install-flash-atten
install-rocm: install-server install-flash-attention-v2-rocm install-vllm-rocm install-rocm: install-server install-flash-attention-v2-rocm install-vllm-rocm
export-requirements: export-requirements:
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 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 accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_intel.txt 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 uv pip compile pyproject.toml --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_rocm.txt --python-version 3.11

212
server/req.txt Normal file
View File

@ -0,0 +1,212 @@
# This file was autogenerated by uv via the following command:
# uv pip compile pyproject.toml --extra attention --extra bnb -o req.txt
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)
bitsandbytes==0.45.1
# via text-generation-server (pyproject.toml)
certifi==2025.1.31
# via requests
charset-normalizer==3.4.1
# via requests
click==8.1.8
# via 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
# via text-generation-server (pyproject.toml)
filelock==3.17.0
# via
# huggingface-hub
# torch
fsspec==2025.2.0
# via
# huggingface-hub
# torch
googleapis-common-protos==1.66.0
# 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
# via
# text-generation-server (pyproject.toml)
# grpc-interceptor
# grpcio-reflection
# grpcio-status
# opentelemetry-exporter-otlp-proto-grpc
grpcio-reflection==1.70.0
# via text-generation-server (pyproject.toml)
grpcio-status==1.70.0
# via text-generation-server (pyproject.toml)
hf-transfer==0.1.9
# via text-generation-server (pyproject.toml)
huggingface-hub==0.28.1
# via tokenizers
idna==3.10
# via requests
importlib-metadata==8.5.0
# via opentelemetry-api
jinja2==3.1.5
# via torch
loguru==0.7.3
# via text-generation-server (pyproject.toml)
markdown-it-py==3.0.0
# via rich
markupsafe==3.0.2
# via jinja2
mdurl==0.1.2
# via markdown-it-py
mpmath==1.3.0
# via sympy
networkx==3.4.2
# via torch
numpy==2.2.2
# via
# text-generation-server (pyproject.toml)
# bitsandbytes
# scipy
nvidia-cublas-cu12==12.4.5.8
# via
# nvidia-cudnn-cu12
# nvidia-cusolver-cu12
# torch
nvidia-cuda-cupti-cu12==12.4.127
# via torch
nvidia-cuda-nvrtc-cu12==12.4.127
# via torch
nvidia-cuda-runtime-cu12==12.4.127
# via torch
nvidia-cudnn-cu12==9.1.0.70
# via torch
nvidia-cufft-cu12==11.2.1.3
# via torch
nvidia-curand-cu12==10.3.5.147
# via torch
nvidia-cusolver-cu12==11.6.1.9
# via torch
nvidia-cusparse-cu12==12.3.1.170
# via
# nvidia-cusolver-cu12
# torch
nvidia-cusparselt-cu12==0.6.2
# via torch
nvidia-nccl-cu12==2.21.5
# via torch
nvidia-nvjitlink-cu12==12.4.127
# via
# nvidia-cusolver-cu12
# nvidia-cusparse-cu12
# torch
nvidia-nvtx-cu12==12.4.127
# via torch
opentelemetry-api==1.30.0
# via
# text-generation-server (pyproject.toml)
# opentelemetry-exporter-otlp-proto-grpc
# opentelemetry-exporter-otlp-proto-http
# opentelemetry-instrumentation
# opentelemetry-instrumentation-grpc
# opentelemetry-sdk
# opentelemetry-semantic-conventions
opentelemetry-exporter-otlp==1.30.0
# via text-generation-server (pyproject.toml)
opentelemetry-exporter-otlp-proto-common==1.30.0
# via
# opentelemetry-exporter-otlp-proto-grpc
# opentelemetry-exporter-otlp-proto-http
opentelemetry-exporter-otlp-proto-grpc==1.30.0
# via opentelemetry-exporter-otlp
opentelemetry-exporter-otlp-proto-http==1.30.0
# via opentelemetry-exporter-otlp
opentelemetry-instrumentation==0.51b0
# via opentelemetry-instrumentation-grpc
opentelemetry-instrumentation-grpc==0.51b0
# via text-generation-server (pyproject.toml)
opentelemetry-proto==1.30.0
# via
# opentelemetry-exporter-otlp-proto-common
# opentelemetry-exporter-otlp-proto-grpc
# opentelemetry-exporter-otlp-proto-http
opentelemetry-sdk==1.30.0
# via
# opentelemetry-exporter-otlp-proto-grpc
# opentelemetry-exporter-otlp-proto-http
opentelemetry-semantic-conventions==0.51b0
# via
# opentelemetry-instrumentation
# opentelemetry-instrumentation-grpc
# opentelemetry-sdk
packaging==24.2
# via
# huggingface-hub
# opentelemetry-instrumentation
pillow==11.1.0
# via text-generation-server (pyproject.toml)
prometheus-client==0.21.1
# via text-generation-server (pyproject.toml)
protobuf==5.29.3
# via
# text-generation-server (pyproject.toml)
# googleapis-common-protos
# grpcio-reflection
# grpcio-status
# opentelemetry-proto
py-cpuinfo==9.0.0
# via text-generation-server (pyproject.toml)
pygments==2.19.1
# via rich
pyyaml==6.0.2
# via huggingface-hub
requests==2.32.3
# via
# huggingface-hub
# opentelemetry-exporter-otlp-proto-http
rich==13.9.4
# via
# text-generation-server (pyproject.toml)
# typer
safetensors==0.5.2
# via text-generation-server (pyproject.toml)
scipy==1.15.1
# via text-generation-server (pyproject.toml)
sentencepiece==0.2.0
# via text-generation-server (pyproject.toml)
setuptools==75.8.0
# via torch
shellingham==1.5.4
# via typer
sympy==1.13.1
# via torch
tokenizers==0.21.0
# via text-generation-server (pyproject.toml)
torch==2.6.0
# via
# attention-kernels
# bitsandbytes
tqdm==4.67.1
# via huggingface-hub
triton==3.2.0
# via torch
typer==0.15.1
# via text-generation-server (pyproject.toml)
typing-extensions==4.12.2
# via
# huggingface-hub
# opentelemetry-sdk
# torch
# typer
urllib3==2.3.0
# via requests
wrapt==1.17.2
# via
# deprecated
# opentelemetry-instrumentation
# opentelemetry-instrumentation-grpc
zipp==3.21.0
# via importlib-metadata

6
server/requirements_cuda.txt
View File

@ -1,5 +1,5 @@
# This file was autogenerated by uv via the following command: # 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 # 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 accelerate==1.3.0
# via # via
# text-generation-server (pyproject.toml) # text-generation-server (pyproject.toml)
@ -123,7 +123,7 @@ markdown-it-py==3.0.0
# via rich # via rich
markupsafe==3.0.2 markupsafe==3.0.2
# via jinja2 # via jinja2
marlin-kernels @ https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp312-cp312-linux_x86_64.whl 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) # via text-generation-server (pyproject.toml)
mdurl==0.1.2 mdurl==0.1.2
# via markdown-it-py # via markdown-it-py
@ -317,8 +317,6 @@ scipy==1.13.1
# via text-generation-server (pyproject.toml) # via text-generation-server (pyproject.toml)
sentencepiece==0.2.0 sentencepiece==0.2.0
# via text-generation-server (pyproject.toml) # via text-generation-server (pyproject.toml)
setuptools==75.2.0
# via torch
shellingham==1.5.4 shellingham==1.5.4
# via typer # via typer
six==1.17.0 six==1.17.0

4
server/requirements_intel.txt
View File

@ -1,5 +1,5 @@
# This file was autogenerated by uv via the following command: # 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 # 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==1.3.0
# via # via
# text-generation-server (pyproject.toml) # text-generation-server (pyproject.toml)
@ -306,8 +306,6 @@ scipy==1.13.1
# via text-generation-server (pyproject.toml) # via text-generation-server (pyproject.toml)
sentencepiece==0.2.0 sentencepiece==0.2.0
# via text-generation-server (pyproject.toml) # via text-generation-server (pyproject.toml)
setuptools==75.2.0
# via torch
shellingham==1.5.4 shellingham==1.5.4
# via typer # via typer
six==1.17.0 six==1.17.0

4
server/requirements_rocm.txt
View File

@ -1,5 +1,5 @@
# This file was autogenerated by uv via the following command: # 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 # 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==1.3.0
# via # via
# text-generation-server (pyproject.toml) # text-generation-server (pyproject.toml)
@ -306,8 +306,6 @@ scipy==1.13.1
# via text-generation-server (pyproject.toml) # via text-generation-server (pyproject.toml)
sentencepiece==0.2.0 sentencepiece==0.2.0
# via text-generation-server (pyproject.toml) # via text-generation-server (pyproject.toml)
setuptools==75.2.0
# via torch
shellingham==1.5.4 shellingham==1.5.4
# via typer # via typer
six==1.17.0 six==1.17.0

18
server/uv.lock
View File

@ -997,15 +997,15 @@ wheels = [
[[package]] [[package]]
name = "moe-kernels" name = "moe-kernels"
version = "0.8.0" version = "0.8.2"
source = { url = "https://github.com/danieldk/moe-kernels/releases/download/v0.8.0/moe_kernels-0.8.0+cu123torch2.5-cp39-abi3-linux_x86_64.whl" } source = { url = "https://github.com/danieldk/moe-kernels/releases/download/v0.8.2/moe_kernels-0.8.2+cu123torch2.5-cp39-abi3-linux_x86_64.whl" }
dependencies = [ dependencies = [
{ name = "nvidia-ml-py" }, { name = "nvidia-ml-py" },
{ name = "torch" }, { name = "torch" },
{ name = "triton" }, { name = "triton" },
] ]
wheels = [ wheels = [
{ url = "https://github.com/danieldk/moe-kernels/releases/download/v0.8.0/moe_kernels-0.8.0+cu123torch2.5-cp39-abi3-linux_x86_64.whl", hash = "sha256:92c4e083c037a325458e731dda6770790495cab273c9bbf5f50fb8e262c099de" }, { url = "https://github.com/danieldk/moe-kernels/releases/download/v0.8.2/moe_kernels-0.8.2+cu123torch2.5-cp39-abi3-linux_x86_64.whl", hash = "sha256:1ed5b26f52339d25ea2513e99e8b6239cf1921af3eac54e03a46bb8f8efb380b" },
] ]
[package.metadata] [package.metadata]
@ -1308,7 +1308,6 @@ name = "nvidia-cublas-cu12"
version = "12.4.5.8" version = "12.4.5.8"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/7f/7f/7fbae15a3982dc9595e49ce0f19332423b260045d0a6afe93cdbe2f1f624/nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0f8aa1706812e00b9f19dfe0cdb3999b092ccb8ca168c0db5b8ea712456fd9b3", size = 363333771 },
{ 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/ae/71/1c91302526c45ab494c23f61c7a84aa568b8c1f9d196efa5993957faf906/nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl", hash = "sha256:2fc8da60df463fdefa81e323eef2e36489e1c94335b5358bcb38360adf75ac9b", size = 363438805 },
] ]
@ -1317,7 +1316,6 @@ name = "nvidia-cuda-cupti-cu12"
version = "12.4.127" version = "12.4.127"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/93/b5/9fb3d00386d3361b03874246190dfec7b206fd74e6e287b26a8fcb359d95/nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:79279b35cf6f91da114182a5ce1864997fd52294a87a16179ce275773799458a", size = 12354556 },
{ 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/67/42/f4f60238e8194a3106d06a058d494b18e006c10bb2b915655bd9f6ea4cb1/nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:9dec60f5ac126f7bb551c055072b69d85392b13311fcc1bcda2202d172df30fb", size = 13813957 },
] ]
@ -1326,7 +1324,6 @@ name = "nvidia-cuda-nvrtc-cu12"
version = "12.4.127" version = "12.4.127"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/77/aa/083b01c427e963ad0b314040565ea396f914349914c298556484f799e61b/nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0eedf14185e04b76aa05b1fea04133e59f465b6f960c0cbf4e37c3cb6b0ea198", size = 24133372 },
{ 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/2c/14/91ae57cd4db3f9ef7aa99f4019cfa8d54cb4caa7e00975df6467e9725a9f/nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a178759ebb095827bd30ef56598ec182b85547f1508941a3d560eb7ea1fbf338", size = 24640306 },
] ]
@ -1335,7 +1332,6 @@ name = "nvidia-cuda-runtime-cu12"
version = "12.4.127" version = "12.4.127"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/a1/aa/b656d755f474e2084971e9a297def515938d56b466ab39624012070cb773/nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:961fe0e2e716a2a1d967aab7caee97512f71767f852f67432d572e36cb3a11f3", size = 894177 },
{ 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/ea/27/1795d86fe88ef397885f2e580ac37628ed058a92ed2c39dc8eac3adf0619/nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:64403288fa2136ee8e467cdc9c9427e0434110899d07c779f25b5c068934faa5", size = 883737 },
] ]
@ -1358,7 +1354,6 @@ dependencies = [
{ name = "nvidia-nvjitlink-cu12" }, { name = "nvidia-nvjitlink-cu12" },
] ]
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/7a/8a/0e728f749baca3fbeffad762738276e5df60851958be7783af121a7221e7/nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_aarch64.whl", hash = "sha256:5dad8008fc7f92f5ddfa2101430917ce2ffacd86824914c82e28990ad7f00399", size = 211422548 },
{ 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/27/94/3266821f65b92b3138631e9c8e7fe1fb513804ac934485a8d05776e1dd43/nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl", hash = "sha256:f083fc24912aa410be21fa16d157fed2055dab1cc4b6934a0e03cba69eb242b9", size = 211459117 },
] ]
@ -1367,7 +1362,6 @@ name = "nvidia-curand-cu12"
version = "10.3.5.147" version = "10.3.5.147"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/80/9c/a79180e4d70995fdf030c6946991d0171555c6edf95c265c6b2bf7011112/nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1f173f09e3e3c76ab084aba0de819c49e56614feae5c12f69883f4ae9bb5fad9", size = 56314811 },
{ 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/8a/6d/44ad094874c6f1b9c654f8ed939590bdc408349f137f9b98a3a23ccec411/nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl", hash = "sha256:a88f583d4e0bb643c49743469964103aa59f7f708d862c3ddb0fc07f851e3b8b", size = 56305206 },
] ]
@ -1381,7 +1375,6 @@ dependencies = [
{ name = "nvidia-nvjitlink-cu12" }, { name = "nvidia-nvjitlink-cu12" },
] ]
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/46/6b/a5c33cf16af09166845345275c34ad2190944bcc6026797a39f8e0a282e0/nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_aarch64.whl", hash = "sha256:d338f155f174f90724bbde3758b7ac375a70ce8e706d70b018dd3375545fc84e", size = 127634111 },
{ 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/3a/e1/5b9089a4b2a4790dfdea8b3a006052cfecff58139d5a4e34cb1a51df8d6f/nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl", hash = "sha256:19e33fa442bcfd085b3086c4ebf7e8debc07cfe01e11513cc6d332fd918ac260", size = 127936057 },
] ]
@ -1393,7 +1386,6 @@ dependencies = [
{ name = "nvidia-nvjitlink-cu12" }, { name = "nvidia-nvjitlink-cu12" },
] ]
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/96/a9/c0d2f83a53d40a4a41be14cea6a0bf9e668ffcf8b004bd65633f433050c0/nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_aarch64.whl", hash = "sha256:9d32f62896231ebe0480efd8a7f702e143c98cfaa0e8a76df3386c1ba2b54df3", size = 207381987 },
{ 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/db/f7/97a9ea26ed4bbbfc2d470994b8b4f338ef663be97b8f677519ac195e113d/nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl", hash = "sha256:ea4f11a2904e2a8dc4b1833cc1b5181cde564edd0d5cd33e3c168eff2d1863f1", size = 207454763 },
] ]
@ -1419,7 +1411,6 @@ name = "nvidia-nvjitlink-cu12"
version = "12.4.127" version = "12.4.127"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/02/45/239d52c05074898a80a900f49b1615d81c07fceadd5ad6c4f86a987c0bc4/nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:4abe7fef64914ccfa909bc2ba39739670ecc9e820c83ccc7a6ed414122599b83", size = 20552510 },
{ 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/ff/ff/847841bacfbefc97a00036e0fce5a0f086b640756dc38caea5e1bb002655/nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:06b3b9b25bf3f8af351d664978ca26a16d2c5127dbd53c0497e28d1fb9611d57", size = 21066810 },
] ]
@ -1428,7 +1419,6 @@ name = "nvidia-nvtx-cu12"
version = "12.4.127" version = "12.4.127"
source = { registry = "https://pypi.org/simple" } source = { registry = "https://pypi.org/simple" }
wheels = [ wheels = [
{ url = "https://files.pythonhosted.org/packages/06/39/471f581edbb7804b39e8063d92fc8305bdc7a80ae5c07dbe6ea5c50d14a5/nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_aarch64.whl", hash = "sha256:7959ad635db13edf4fc65c06a6e9f9e55fc2f92596db928d169c0bb031e88ef3", size = 100417 },
{ 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/87/20/199b8713428322a2f22b722c62b8cc278cc53dffa9705d744484b5035ee9/nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:781e950d9b9f60d8241ccea575b32f5105a5baf4c2351cab5256a24869f12a1a", size = 99144 },
] ]
@ -2746,7 +2736,7 @@ requires-dist = [
{ name = "marlin-kernels", marker = "python_full_version == '3.10.*' and extra == 'marlin'", url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp310-cp310-linux_x86_64.whl" }, { name = "marlin-kernels", marker = "python_full_version == '3.10.*' and extra == 'marlin'", url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp310-cp310-linux_x86_64.whl" },
{ name = "marlin-kernels", marker = "python_full_version == '3.11.*' and extra == 'marlin'", url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp311-cp311-linux_x86_64.whl" }, { name = "marlin-kernels", marker = "python_full_version == '3.11.*' and extra == 'marlin'", url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp311-cp311-linux_x86_64.whl" },
{ name = "marlin-kernels", marker = "python_full_version == '3.12.*' and extra == 'marlin'", url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp312-cp312-linux_x86_64.whl" }, { name = "marlin-kernels", marker = "python_full_version == '3.12.*' and extra == 'marlin'", url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp312-cp312-linux_x86_64.whl" },
{ name = "moe-kernels", marker = "extra == 'moe'", url = "https://github.com/danieldk/moe-kernels/releases/download/v0.8.0/moe_kernels-0.8.0+cu123torch2.5-cp39-abi3-linux_x86_64.whl" }, { name = "moe-kernels", marker = "extra == 'moe'", url = "https://github.com/danieldk/moe-kernels/releases/download/v0.8.2/moe_kernels-0.8.2+cu123torch2.5-cp39-abi3-linux_x86_64.whl" },
{ name = "mypy-protobuf", marker = "extra == 'gen'", specifier = ">=3.6.0" }, { name = "mypy-protobuf", marker = "extra == 'gen'", specifier = ">=3.6.0" },
{ name = "numpy", specifier = ">=1.26,<3" }, { name = "numpy", specifier = ">=1.26,<3" },
{ name = "opentelemetry-api", specifier = ">=1.27.0" }, { name = "opentelemetry-api", specifier = ">=1.27.0" },