mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-05-20 17:22:09 +00:00
7e531f413d
* Update to Torch 2.7.0 * Try to fix typer/click issue * Pin click to fix incompatibility with typer * Fix some test outputs with slight deviations * Attempt again to sync with CI * Mamba too * Fixup mllama Also switch to `unsloth/Llama-3.2-11B-Vision-Instruct` for testing from the EU :).
391 lines
9.0 KiB
Plaintext
391 lines
9.0 KiB
Plaintext
# This file was autogenerated by uv via the following command:
|
|
# 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==2.6.1
|
|
# via aiohttp
|
|
aiohttp==3.11.18
|
|
# via
|
|
# datasets
|
|
# fsspec
|
|
aiosignal==1.3.2
|
|
# via aiohttp
|
|
airportsdata==20250224
|
|
# via outlines
|
|
annotated-types==0.7.0
|
|
# via pydantic
|
|
attrs==25.3.0
|
|
# via
|
|
# aiohttp
|
|
# jsonschema
|
|
# referencing
|
|
bitsandbytes==0.45.5
|
|
# via text-generation-server (pyproject.toml)
|
|
certifi==2025.4.26
|
|
# via requests
|
|
charset-normalizer==3.4.2
|
|
# via requests
|
|
click==8.1.8
|
|
# via
|
|
# text-generation-server (pyproject.toml)
|
|
# typer
|
|
cloudpickle==3.1.1
|
|
# via outlines
|
|
compressed-tensors==0.9.4
|
|
# via text-generation-server (pyproject.toml)
|
|
datasets==2.21.0
|
|
# via text-generation-server (pyproject.toml)
|
|
deprecated==1.2.18
|
|
# via
|
|
# opentelemetry-api
|
|
# opentelemetry-exporter-otlp-proto-grpc
|
|
# opentelemetry-exporter-otlp-proto-http
|
|
# opentelemetry-semantic-conventions
|
|
dill==0.3.8
|
|
# via
|
|
# datasets
|
|
# multiprocess
|
|
diskcache==5.6.3
|
|
# via outlines
|
|
einops==0.8.1
|
|
# via text-generation-server (pyproject.toml)
|
|
filelock==3.18.0
|
|
# via
|
|
# datasets
|
|
# huggingface-hub
|
|
# torch
|
|
# transformers
|
|
frozenlist==1.6.0
|
|
# via
|
|
# aiohttp
|
|
# aiosignal
|
|
fsspec==2024.6.1
|
|
# via
|
|
# datasets
|
|
# huggingface-hub
|
|
# torch
|
|
genson==1.3.0
|
|
# via outlines
|
|
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==1.71.0
|
|
# via
|
|
# text-generation-server (pyproject.toml)
|
|
# grpc-interceptor
|
|
# grpcio-reflection
|
|
# grpcio-status
|
|
# opentelemetry-exporter-otlp-proto-grpc
|
|
grpcio-reflection==1.71.0
|
|
# via text-generation-server (pyproject.toml)
|
|
grpcio-status==1.71.0
|
|
# via text-generation-server (pyproject.toml)
|
|
hf-transfer==0.1.9
|
|
# via text-generation-server (pyproject.toml)
|
|
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
|
|
idna==3.10
|
|
# via
|
|
# requests
|
|
# yarl
|
|
importlib-metadata==8.6.1
|
|
# via opentelemetry-api
|
|
interegular==0.3.3
|
|
# via
|
|
# outlines
|
|
# outlines-core
|
|
iso3166==2.1.1
|
|
# via outlines
|
|
jinja2==3.1.6
|
|
# via
|
|
# outlines
|
|
# torch
|
|
jsonschema==4.23.0
|
|
# via
|
|
# outlines
|
|
# outlines-core
|
|
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
|
|
# 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
|
|
multidict==6.4.3
|
|
# via
|
|
# aiohttp
|
|
# yarl
|
|
multiprocess==0.70.16
|
|
# via datasets
|
|
nest-asyncio==1.6.0
|
|
# via outlines
|
|
networkx==3.4.2
|
|
# via torch
|
|
numpy==2.2.5
|
|
# via
|
|
# text-generation-server (pyproject.toml)
|
|
# accelerate
|
|
# bitsandbytes
|
|
# datasets
|
|
# outlines
|
|
# pandas
|
|
# peft
|
|
# scipy
|
|
# transformers
|
|
nvidia-cublas-cu12==12.6.4.1
|
|
# via
|
|
# nvidia-cudnn-cu12
|
|
# nvidia-cusolver-cu12
|
|
# torch
|
|
nvidia-cuda-cupti-cu12==12.6.80
|
|
# via torch
|
|
nvidia-cuda-nvrtc-cu12==12.6.77
|
|
# via torch
|
|
nvidia-cuda-runtime-cu12==12.6.77
|
|
# via torch
|
|
nvidia-cudnn-cu12==9.5.1.17
|
|
# via torch
|
|
nvidia-cufft-cu12==11.3.0.4
|
|
# via torch
|
|
nvidia-cufile-cu12==1.11.1.6
|
|
# via torch
|
|
nvidia-curand-cu12==10.3.7.77
|
|
# via torch
|
|
nvidia-cusolver-cu12==11.7.1.2
|
|
# via torch
|
|
nvidia-cusparse-cu12==12.5.4.2
|
|
# via
|
|
# nvidia-cusolver-cu12
|
|
# torch
|
|
nvidia-cusparselt-cu12==0.6.3
|
|
# via torch
|
|
nvidia-nccl-cu12==2.26.2
|
|
# via torch
|
|
nvidia-nvjitlink-cu12==12.6.85
|
|
# via
|
|
# nvidia-cufft-cu12
|
|
# nvidia-cusolver-cu12
|
|
# nvidia-cusparse-cu12
|
|
# torch
|
|
nvidia-nvtx-cu12==12.6.77
|
|
# via torch
|
|
opentelemetry-api==1.33.0
|
|
# 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==1.33.0
|
|
# via text-generation-server (pyproject.toml)
|
|
opentelemetry-exporter-otlp-proto-common==1.33.0
|
|
# via
|
|
# opentelemetry-exporter-otlp-proto-grpc
|
|
# opentelemetry-exporter-otlp-proto-http
|
|
opentelemetry-exporter-otlp-proto-grpc==1.33.0
|
|
# via opentelemetry-exporter-otlp
|
|
opentelemetry-exporter-otlp-proto-http==1.33.0
|
|
# via opentelemetry-exporter-otlp
|
|
opentelemetry-instrumentation==0.54b0
|
|
# via opentelemetry-instrumentation-grpc
|
|
opentelemetry-instrumentation-grpc==0.54b0
|
|
# via text-generation-server (pyproject.toml)
|
|
opentelemetry-proto==1.33.0
|
|
# via
|
|
# opentelemetry-exporter-otlp-proto-common
|
|
# opentelemetry-exporter-otlp-proto-grpc
|
|
# opentelemetry-exporter-otlp-proto-http
|
|
opentelemetry-sdk==1.33.0
|
|
# via
|
|
# opentelemetry-exporter-otlp-proto-grpc
|
|
# opentelemetry-exporter-otlp-proto-http
|
|
opentelemetry-semantic-conventions==0.54b0
|
|
# via
|
|
# opentelemetry-instrumentation
|
|
# opentelemetry-instrumentation-grpc
|
|
# opentelemetry-sdk
|
|
outlines==0.2.3
|
|
# via text-generation-server (pyproject.toml)
|
|
outlines-core==0.1.26
|
|
# via outlines
|
|
packaging==25.0
|
|
# via
|
|
# accelerate
|
|
# datasets
|
|
# huggingface-hub
|
|
# kernels
|
|
# opentelemetry-instrumentation
|
|
# peft
|
|
# transformers
|
|
pandas==2.2.3
|
|
# via datasets
|
|
peft==0.15.2
|
|
# via text-generation-server (pyproject.toml)
|
|
pillow==11.2.1
|
|
# via text-generation-server (pyproject.toml)
|
|
prometheus-client==0.21.1
|
|
# via text-generation-server (pyproject.toml)
|
|
propcache==0.3.1
|
|
# via
|
|
# aiohttp
|
|
# yarl
|
|
protobuf==5.29.4
|
|
# via
|
|
# text-generation-server (pyproject.toml)
|
|
# googleapis-common-protos
|
|
# grpcio-reflection
|
|
# grpcio-status
|
|
# opentelemetry-proto
|
|
psutil==7.0.0
|
|
# via
|
|
# accelerate
|
|
# peft
|
|
py-cpuinfo==9.0.0
|
|
# via text-generation-server (pyproject.toml)
|
|
pyarrow==20.0.0
|
|
# via datasets
|
|
pydantic==2.11.4
|
|
# via
|
|
# compressed-tensors
|
|
# outlines
|
|
pydantic-core==2.33.2
|
|
# via pydantic
|
|
pygments==2.19.1
|
|
# via rich
|
|
python-dateutil==2.9.0.post0
|
|
# via pandas
|
|
pytz==2025.2
|
|
# via pandas
|
|
pyyaml==6.0.2
|
|
# via
|
|
# accelerate
|
|
# datasets
|
|
# huggingface-hub
|
|
# peft
|
|
# transformers
|
|
referencing==0.36.2
|
|
# via
|
|
# jsonschema
|
|
# jsonschema-specifications
|
|
# outlines
|
|
regex==2024.11.6
|
|
# via transformers
|
|
requests==2.32.3
|
|
# via
|
|
# datasets
|
|
# huggingface-hub
|
|
# opentelemetry-exporter-otlp-proto-http
|
|
# outlines
|
|
# transformers
|
|
rich==14.0.0
|
|
# via
|
|
# text-generation-server (pyproject.toml)
|
|
# typer
|
|
rpds-py==0.24.0
|
|
# via
|
|
# jsonschema
|
|
# referencing
|
|
safetensors==0.5.3
|
|
# via
|
|
# text-generation-server (pyproject.toml)
|
|
# accelerate
|
|
# peft
|
|
# transformers
|
|
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==1.14.0
|
|
# via torch
|
|
texttable==1.7.0
|
|
# via text-generation-server (pyproject.toml)
|
|
tokenizers==0.21.1
|
|
# via
|
|
# text-generation-server (pyproject.toml)
|
|
# transformers
|
|
torch==2.7.0
|
|
# via
|
|
# accelerate
|
|
# bitsandbytes
|
|
# compressed-tensors
|
|
# outlines
|
|
# peft
|
|
tqdm==4.67.1
|
|
# via
|
|
# datasets
|
|
# huggingface-hub
|
|
# outlines
|
|
# peft
|
|
# transformers
|
|
transformers==4.51.3
|
|
# via
|
|
# text-generation-server (pyproject.toml)
|
|
# compressed-tensors
|
|
# peft
|
|
triton==3.3.0
|
|
# via torch
|
|
typer==0.15.3
|
|
# via text-generation-server (pyproject.toml)
|
|
typing-extensions==4.13.2
|
|
# via
|
|
# huggingface-hub
|
|
# opentelemetry-sdk
|
|
# outlines
|
|
# pydantic
|
|
# pydantic-core
|
|
# referencing
|
|
# torch
|
|
# typer
|
|
# typing-inspection
|
|
typing-inspection==0.4.0
|
|
# via pydantic
|
|
tzdata==2025.2
|
|
# via pandas
|
|
urllib3==2.4.0
|
|
# via requests
|
|
wrapt==1.17.2
|
|
# via
|
|
# deprecated
|
|
# opentelemetry-instrumentation
|
|
# opentelemetry-instrumentation-grpc
|
|
xxhash==3.5.0
|
|
# via datasets
|
|
yarl==1.20.0
|
|
# via aiohttp
|
|
zipp==3.21.0
|
|
# via importlib-metadata
|