mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-19 22:02:06 +00:00
213 lines
5.7 KiB
Plaintext
213 lines
5.7 KiB
Plaintext
|
# 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
|