diff --git a/requirements/common.txt b/requirements/common.txt index 748ffe88f4..c78d5a44ee 100644 --- a/requirements/common.txt +++ b/requirements/common.txt @@ -3,32 +3,32 @@ cachetools psutil sentencepiece # Required for LLaMA tokenizer. numpy -requests >= 2.26.0 +requests >= 2.34.2 tqdm blake3 py-cpuinfo transformers >= 5.5.3 -tokenizers >= 0.21.1 # Required for fast incremental detokenization. +tokenizers >= 0.23.1 # Required for fast incremental detokenization. safetensors >= 0.6.2 # MXFP4/MXFP6 dtype support (F8_E8M0, F4) added in 0.6.0: https://github.com/huggingface/safetensors/pull/611 protobuf >= 5.29.6, !=6.30.*, !=6.31.*, !=6.32.*, !=6.33.0.*, !=6.33.1.*, !=6.33.2.*, !=6.33.3.*, !=6.33.4.* # Required by LlamaTokenizer, gRPC. CVE-2026-0994 -fastapi[standard] >= 0.133.0, < 0.137.0 # First version supporting Starlette 1.0; < 0.137.0 avoids route-tree change that breaks model-hosting-container-standards handler overrides. -starlette >= 1.0.1 # CVE-2026-48710: Host header injection in < 1.0.1 -aiohttp >= 3.13.3 -openai >= 2.0.0 # For Responses API with reasoning content -pydantic >= 2.12.0 -prometheus_client >= 0.18.0 +fastapi[standard] >= 0.141.1, < 0.142.0 # First version supporting Starlette 1.0; < 0.137.0 avoids route-tree change that breaks model-hosting-container-standards handler overrides. +starlette >= 1.5.1 # CVE-2026-48710: Host header injection in < 1.0.1 +aiohttp >= 3.14.3 +openai >= 2.53.0 # For Responses API with reasoning content +pydantic >= 2.13.4 +prometheus_client >= 0.26.0 pillow # Required for image processing -prometheus-fastapi-instrumentator >= 8.0.0 # v8 unblocks starlette >= 1.0 -tiktoken >= 0.6.0 # Required for DBRX tokenizer +prometheus-fastapi-instrumentator >= 8.1.0 # v8 unblocks starlette >= 1.0 +tiktoken >= 0.13.0 # Required for DBRX tokenizer lm-format-enforcer == 0.11.3 llguidance >= 1.7.0, < 1.8.0; platform_machine == "x86_64" or platform_machine == "arm64" or platform_machine == "aarch64" or platform_machine == "ppc64le" or platform_machine == "s390x" outlines_core == 0.2.14 -lark == 1.2.2 +lark == 1.3.1 xgrammar >= 0.2.1, < 1.0.0; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64" or platform_machine == "s390x" or platform_machine == "ppc64le" -typing_extensions >= 4.10 -filelock >= 3.16.1 # need to contain https://github.com/tox-dev/filelock/pull/317 +typing_extensions >= 4.16.0 +filelock >= 3.32.2 # need to contain https://github.com/tox-dev/filelock/pull/317 partial-json-parser # used for parsing partial JSON outputs -jsonschema >= 4.23.0 # required for MiniMax M3 tool schema validation +jsonschema >= 4.26.0 # required for MiniMax M3 tool schema validation pyzmq >= 25.0.0 msgspec mistral_common[image] >= 1.11.6 @@ -48,10 +48,10 @@ cbor2 # Required for cross-language serialization of hashable objects ijson # Required for mistral streaming tool parser setproctitle # Used to set process names for better debugging and monitoring openai-harmony >= 0.0.3 # Required for gpt-oss -anthropic >= 0.71.0 +anthropic >= 0.121.0 model-hosting-container-standards >= 0.1.14, < 1.0.0 mcp -opentelemetry-sdk >= 1.27.0 -opentelemetry-api >= 1.27.0 -opentelemetry-exporter-otlp >= 1.27.0 -opentelemetry-semantic-conventions-ai >= 0.4.1 +opentelemetry-sdk >= 1.44.0 +opentelemetry-api >= 1.44.0 +opentelemetry-exporter-otlp >= 1.44.0 +opentelemetry-semantic-conventions-ai >= 0.5.1 diff --git a/requirements/cpu.txt b/requirements/cpu.txt index 30e47a8cab..b722d4958f 100644 --- a/requirements/cpu.txt +++ b/requirements/cpu.txt @@ -3,7 +3,7 @@ setuptools==77.0.3 # this version can reuse CMake build dir -numba == 0.65.0; platform_machine != "s390x" # Required for N-gram speculative decoding +numba == 0.66.0; platform_machine != "s390x" # Required for N-gram speculative decoding # Dependencies for CPUs torch==2.13.0+cpu; platform_machine == "x86_64" or platform_machine == "s390x" or platform_machine == "aarch64" @@ -16,7 +16,7 @@ torchaudio; platform_machine != "s390x" and platform_machine != "riscv64" torchvision; platform_machine != "s390x" and platform_machine != "riscv64" # required for the torchcodec video decoding backend -torchcodec >= 0.14; platform_machine != "s390x" and platform_machine != "riscv64" and platform_machine != "ppc64le" +torchcodec >= 0.15.0; platform_machine != "s390x" and platform_machine != "riscv64" and platform_machine != "ppc64le" # Intel Extension for PyTorch, only for x86_64 CPUs intel-openmp==2024.2.1; platform_machine == "x86_64" diff --git a/requirements/cuda.txt b/requirements/cuda.txt index 2a8b2734f8..8ae8450622 100644 --- a/requirements/cuda.txt +++ b/requirements/cuda.txt @@ -1,15 +1,15 @@ # Common dependencies -r common.txt -numba == 0.65.0 # Required for N-gram speculative decoding +numba == 0.66.0 # Required for N-gram speculative decoding # Dependencies for NVIDIA GPUs torch==2.13.0 torchaudio==2.11.0 # These must be updated alongside torch torchvision==0.28.0 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version -torchcodec >= 0.14 -PyNvVideoCodec==2.0.4 +torchcodec >= 0.15.0 +PyNvVideoCodec==2.2.0 # FlashInfer should be updated together with the Dockerfile # flashinfer-cubin is not on PyPI since 0.6.14; setup.py excludes it from # install_requires so the published wheel does not carry an unresolvable pin @@ -25,11 +25,11 @@ nvtx==0.2.15 fastsafetensors >= 0.3.2 # QuACK and Cutlass DSL for FA4 (cute-DSL implementation) -nvidia-cutlass-dsl[cu13]==4.6.0 +nvidia-cutlass-dsl[cu13]==4.7.0 quack-kernels>=0.6.1 # Required for CUTLASS DSL 4.6 by MSA # Tokenspeed_MLA for faster mla with spec decode -tokenspeed-mla==0.1.8; platform_system == "Linux" +tokenspeed-mla==0.2.4; platform_system == "Linux" # Humming kernels for quantization gemm humming-kernels[cu13]==0.1.10 diff --git a/requirements/docs.txt b/requirements/docs.txt index 5331a3b79b..61ae1c2930 100644 --- a/requirements/docs.txt +++ b/requirements/docs.txt @@ -30,7 +30,7 @@ gitdb==4.0.12 # via gitpython gitpython==3.1.50 # via mkdocs-git-revision-date-localized-plugin -griffelib==2.0.2 +griffelib==2.1.0 # via mkdocstrings-python htmlmin2==0.1.13 # via mkdocs-minify-plugin @@ -157,7 +157,7 @@ regex==2026.4.4 # via -r requirements/docs.in requests==2.33.1 # via mkdocs-material -ruff==0.15.12 +ruff==0.16.2 # via -r requirements/docs.in selectolax==0.4.8 # via mkdocs-glightbox @@ -167,6 +167,7 @@ smmap==5.0.3 # via gitdb typing-extensions==4.15.0 # via + # mkdocstrings-python # pydantic # pydantic-core # typing-inspection diff --git a/requirements/rocm.txt b/requirements/rocm.txt index b5bcdf4b33..2b8c37a6b4 100644 --- a/requirements/rocm.txt +++ b/requirements/rocm.txt @@ -2,22 +2,22 @@ -r common.txt # The version of gRPC libraries should be consistent with each other -grpcio==1.78.0 -grpcio-reflection==1.78.0 +grpcio==1.83.0 +grpcio-reflection==1.83.0 -numba == 0.65.0 # Required for N-gram speculative decoding +numba == 0.66.0 # Required for N-gram speculative decoding # Dependencies for AMD GPUs datasets peft pytest-asyncio -tensorizer==2.10.1 +tensorizer==2.12.1 packaging>=24.2 setuptools>=77.0.3,<80.0.0 setuptools-scm>=8 setuptools-rust>=1.9.0 -runai-model-streamer[s3,gcs,azure]==0.15.7 -conch-triton-kernels==1.2.1 +runai-model-streamer[s3,gcs,azure]==0.16.1 +conch-triton-kernels==1.3 timm>=1.0.17 # amd-quark: required for Quark quantization on ROCm # To be consistent with test_quark.py diff --git a/requirements/test/cuda.txt b/requirements/test/cuda.txt index 192f3ac5a6..8e3efcfe9f 100644 --- a/requirements/test/cuda.txt +++ b/requirements/test/cuda.txt @@ -2,13 +2,13 @@ # uv pip compile requirements/test/cuda.in -c requirements/cuda.txt -o requirements/test/cuda.txt --index-strategy unsafe-best-match --torch-backend cu130 --python-platform x86_64-manylinux_2_28 --python-version 3.12 abi3info==2025.11.29 # via torch-abi-audit -absl-py==2.1.0 +absl-py==2.5.0 # via rouge-score -accelerate==1.13.0 +accelerate==1.14.0 # via peft -aiohappyeyeballs==2.6.1 +aiohappyeyeballs==2.7.1 # via aiohttp -aiohttp==3.13.3 +aiohttp==3.14.3 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -24,15 +24,15 @@ aiosignal==1.4.0 # via aiohttp albumentations==1.4.6 # via -r requirements/test/cuda.in -alembic==1.16.4 +alembic==1.19.1 # via optuna annotated-doc==0.0.4 # via # fastapi # typer -annotated-types==0.7.0 +annotated-types==0.8.0 # via pydantic -anthropic==0.112.0 +anthropic==0.121.0 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -49,9 +49,9 @@ apache-tvm-ffi==0.1.11 # via # -c requirements/cuda.txt # xgrammar -arctic-inference==0.1.1 +arctic-inference==0.2.0 # via -r requirements/test/cuda.in -argcomplete==3.5.1 +argcomplete==3.7.2 # via datamodel-code-generator astor==0.8.1 # via depyf @@ -61,35 +61,35 @@ attrs==24.2.0 # hypothesis # jsonschema # referencing -audioread==3.0.1 +audioread==3.1.0 # via librosa av==16.1.0 # via -r requirements/test/cuda.in -azure-core==1.38.2 +azure-core==1.41.0 # via # azure-identity # azure-storage-blob azure-identity==1.25.2 # via runai-model-streamer-azure -azure-storage-blob==12.28.0 +azure-storage-blob==12.30.0 # via runai-model-streamer-azure backoff==2.2.1 # via -r requirements/test/cuda.in -bitsandbytes==0.49.2 +bitsandbytes==0.50.0 # via -r requirements/test/cuda.in black==24.10.0 # via datamodel-code-generator blake3==1.0.9 # via -r requirements/test/../common.txt -blobfile==3.0.0 +blobfile==3.2.0 # via -r requirements/test/cuda.in -bm25s==0.2.13 +bm25s==0.3.10 # via mteb -boto3==1.35.57 +boto3==1.43.67 # via # runai-model-streamer-s3 # tensorizer -botocore==1.35.57 +botocore==1.43.67 # via # boto3 # s3transfer @@ -109,7 +109,7 @@ certifi==2024.8.30 # httpx # requests # sentry-sdk -cffi==2.0.0 +cffi==2.1.1 # via # cryptography # soundfile @@ -131,7 +131,7 @@ click==8.4.2 # uvicorn cloudpickle==3.1.2 # via -r requirements/test/../common.txt -cohere-melody==0.9.0 +cohere-melody==0.13.0 # via -r requirements/test/cuda.in colorama==0.4.6 # via @@ -139,7 +139,7 @@ colorama==0.4.6 # sacrebleu colorful==0.5.6 # via ray -colorlog==6.10.1 +colorlog==6.12.0 # via optuna compressed-tensors==0.17.0 # via @@ -147,9 +147,9 @@ compressed-tensors==0.17.0 # -r requirements/test/../common.txt contourpy==1.3.0 # via matplotlib -coverage==7.10.6 +coverage==7.15.4 # via pytest-cov -cramjam==2.9.0 +cramjam==2.11.0 # via fastparquet cryptography==46.0.5 # via @@ -157,19 +157,19 @@ cryptography==46.0.5 # azure-storage-blob # msal # pyjwt -cuda-bindings==13.0.3 +cuda-bindings==13.3.1 # via torch -cuda-pathfinder==1.3.3 +cuda-pathfinder==1.6.0 # via cuda-bindings -cuda-toolkit==13.0.3.0 +cuda-toolkit==13.3.1 # via torch cupy-cuda12x==13.6.0 # via ray cycler==0.12.1 # via matplotlib -datamodel-code-generator==0.26.3 +datamodel-code-generator==0.72.2 # via -r requirements/test/cuda.in -dataproperty==1.0.1 +dataproperty==1.1.1 # via # pytablewriter # tabledata @@ -179,7 +179,7 @@ datasets==3.3.0 # evaluate # lm-eval # mteb -decorator==5.1.1 +decorator==5.3.1 # via librosa decord==0.6.0 # via -r requirements/test/cuda.in @@ -189,22 +189,22 @@ depyf==0.20.0 # -r requirements/test/../common.txt detect-installer==0.1.0 # via fastapi-cloud-cli -dill==0.3.8 +dill==0.4.1 # via # datasets # depyf # evaluate # lm-eval # multiprocess -distlib==0.3.9 +distlib==0.4.3 # via virtualenv distro==1.9.0 # via # anthropic # openai -dnspython==2.7.0 +dnspython==2.8.0 # via email-validator -docker==7.1.0 +docker==7.2.0 # via gpt-oss docopt==0.6.2 # via num2words @@ -216,9 +216,9 @@ einops==0.8.1 # encodec # vector-quantize-pytorch # vocos -einx==0.3.0 +einx==0.4.3 # via vector-quantize-pytorch -email-validator==2.2.0 +email-validator==2.3.0 # via # fastapi # pydantic @@ -228,7 +228,7 @@ et-xmlfile==2.0.0 # via openpyxl evaluate==0.4.3 # via lm-eval -fastapi==0.136.3 +fastapi==0.141.1 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -236,7 +236,7 @@ fastapi==0.136.3 # model-hosting-container-standards fastapi-cli==0.0.27 # via fastapi -fastapi-cloud-cli==0.21.0 +fastapi-cloud-cli==0.23.0 # via fastapi-cli fastar==0.11.0 # via @@ -250,7 +250,7 @@ fastsafetensors==0.3.2 # via # -c requirements/cuda.txt # -r requirements/test/cuda.in -filelock==3.16.1 +filelock==3.32.2 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -260,11 +260,11 @@ filelock==3.16.1 # ray # torch # virtualenv -fonttools==4.55.0 +fonttools==4.63.0 # via matplotlib frozendict==2.4.6 # via einx -frozenlist==1.5.0 +frozenlist==1.8.0 # via # aiohttp # aiosignal @@ -279,30 +279,30 @@ ftfy==6.3.1 # via open-clip-torch genai-perf==0.0.16 # via -r requirements/test/cuda.in -genson==1.3.0 +genson==1.4.0 # via datamodel-code-generator -google-api-core==2.24.2 +google-api-core==2.34.0 # via # google-cloud-core # google-cloud-storage # opencensus -google-auth==2.40.2 +google-auth==2.56.3 # via # google-api-core # google-cloud-core # google-cloud-storage # runai-model-streamer-gcs -google-cloud-core==2.4.3 +google-cloud-core==2.6.1 # via google-cloud-storage -google-cloud-storage==3.4.0 +google-cloud-storage==3.13.1 # via runai-model-streamer-gcs -google-crc32c==1.7.1 +google-crc32c==1.8.0 # via # google-cloud-storage # google-resumable-media -google-resumable-media==2.7.2 +google-resumable-media==2.10.1 # via google-cloud-storage -googleapis-common-protos==1.70.0 +googleapis-common-protos==1.75.1 # via # google-api-core # opentelemetry-exporter-otlp-proto-grpc @@ -311,29 +311,29 @@ gpt-oss==0.0.8 # via -r requirements/test/cuda.in graphql-core==3.2.6 # via hypothesis-graphql -greenlet==3.2.3 +greenlet==3.5.4 # via sqlalchemy -grpcio==1.78.0 +grpcio==1.83.0 # via # -r requirements/test/cuda.in # grpcio-reflection # opentelemetry-exporter-otlp-proto-grpc # ray -grpcio-reflection==1.78.0 +grpcio-reflection==1.83.0 # via -r requirements/test/cuda.in -h11==0.14.0 +h11==0.16.0 # via # httpcore # uvicorn -h2==4.3.0 +h2==4.4.1 # via httpx harfile==0.5.0 # via schemathesis -hf-xet==1.5.1 +hf-xet==1.6.0 # via huggingface-hub -hiredis==3.0.0 +hiredis==3.4.1 # via tensorizer -hpack==4.1.0 +hpack==4.2.0 # via h2 html2text==2025.4.15 # via gpt-oss @@ -341,7 +341,7 @@ httpcore==1.0.6 # via httpx httptools==0.8.0 # via uvicorn -httpx==0.27.2 +httpx==0.28.1 # via # -r requirements/test/cuda.in # anthropic @@ -355,7 +355,7 @@ httpx==0.27.2 # schemathesis httpx-sse==0.4.3 # via mcp -huggingface-hub==1.22.0 +huggingface-hub==1.27.0 # via # accelerate # datasets @@ -368,11 +368,11 @@ huggingface-hub==1.22.0 # tokenizers # transformers # vocos -humanize==4.11.0 +humanize==4.16.0 # via runai-model-streamer hyperframe==6.1.0 # via h2 -hypothesis==6.131.0 +hypothesis==6.165.2 # via # hypothesis-graphql # hypothesis-jsonschema @@ -381,7 +381,7 @@ hypothesis-graphql==0.13.0 # via schemathesis hypothesis-jsonschema==0.23.1 # via schemathesis -idna==3.10 +idna==3.18 # via # anyio # email-validator @@ -398,7 +398,7 @@ importlib-metadata==8.7.0 # via opentelemetry-api inflect==5.6.2 # via datamodel-code-generator -iniconfig==2.0.0 +iniconfig==2.3.0 # via pytest instanttensor==0.1.9 # via -r requirements/test/cuda.in @@ -415,23 +415,23 @@ jinja2==3.1.6 # genai-perf # lm-eval # torch -jiter==0.15.0 +jiter==0.16.0 # via # anthropic # openai jiwer==3.0.5 # via -r requirements/test/cuda.in -jmespath==1.0.1 +jmespath==1.1.0 # via # boto3 # botocore # model-hosting-container-standards -joblib==1.4.2 +joblib==1.5.3 # via # librosa # nltk # scikit-learn -jsonschema==4.23.0 +jsonschema==4.26.0 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -439,7 +439,7 @@ jsonschema==4.23.0 # mcp # mistral-common # ray -jsonschema-rs==0.46.5 +jsonschema-rs==0.49.7 # via schemathesis jsonschema-specifications==2024.10.1 # via jsonschema @@ -449,25 +449,25 @@ kaldi-native-fbank==1.22.3 # via -r requirements/test/cuda.in kaleido==0.2.1 # via genai-perf -kiwisolver==1.4.7 +kiwisolver==1.5.0 # via matplotlib -lark==1.2.2 +lark==1.3.1 # via # -c requirements/common.txt # -r requirements/test/../common.txt -lazy-loader==0.4 +lazy-loader==0.5 # via # librosa # scikit-image libnacl==2.1.0 # via tensorizer -librosa==0.10.2.post1 +librosa==0.11.0 # via -r requirements/test/cuda.in llguidance==1.7.6 # via # -c requirements/common.txt # -r requirements/test/../common.txt -llvmlite==0.47.0 +llvmlite==0.48.0 # via numba lm-eval==0.4.12 # via -r requirements/test/cuda.in @@ -482,7 +482,7 @@ lxml==5.3.0 # blobfile # gpt-oss # sacrebleu -mako==1.3.10 +mako==1.4.1 # via alembic markdown-it-py==3.0.0 # via rich @@ -491,7 +491,7 @@ markupsafe==3.0.1 # jinja2 # mako # werkzeug -matplotlib==3.9.2 +matplotlib==3.10.9 # via -r requirements/test/cuda.in mbstrdecoder==1.1.3 # via @@ -513,23 +513,23 @@ model-hosting-container-standards==0.1.16 # -r requirements/test/../common.txt more-itertools==10.5.0 # via lm-eval -mpmath==1.3.0 +mpmath==1.4.1 # via sympy -msal==1.34.0 +msal==1.37.0 # via # azure-identity # msal-extensions msal-extensions==1.3.1 # via azure-identity -msgpack==1.1.0 +msgpack==1.2.1 # via # librosa # ray msgspec==0.21.1 # via -r requirements/test/../common.txt -mteb==2.8.3 +mteb==2.18.16 # via -r requirements/test/cuda.in -multidict==6.1.0 +multidict==6.7.1 # via # aiohttp # yarl @@ -537,19 +537,19 @@ multiprocess==0.70.16 # via # datasets # evaluate -mypy-extensions==1.0.0 +mypy-extensions==1.1.0 # via black -networkx==3.2.1 +networkx==3.4.2 # via # scikit-image # torch ninja==1.13.0 # via -r requirements/test/../common.txt -nltk==3.9.1 +nltk==3.10.2 # via rouge-score num2words==0.5.14 # via -r requirements/test/cuda.in -numba==0.65.0 +numba==0.66.0 # via # -c requirements/cuda.txt # -r requirements/test/cuda.in @@ -601,50 +601,50 @@ numpy==2.2.6 # tritonclient # vocos # xgrammar -nvidia-cublas==13.1.1.3 +nvidia-cublas==13.6.1.10 # via # cuda-toolkit # nvidia-cudnn-cu13 # nvidia-cusolver -nvidia-cuda-cupti==13.0.85 +nvidia-cuda-cupti==13.3.75 # via cuda-toolkit -nvidia-cuda-nvrtc==13.0.88 +nvidia-cuda-nvrtc==13.3.33 # via # cuda-toolkit # nvidia-cublas -nvidia-cuda-runtime==13.0.96 +nvidia-cuda-runtime==13.3.29 # via cuda-toolkit -nvidia-cudnn-cu13==9.20.0.48 +nvidia-cudnn-cu13==9.24.0.43 # via torch -nvidia-cufft==12.0.0.61 +nvidia-cufft==12.3.0.29 # via cuda-toolkit -nvidia-cufile==1.15.1.6 +nvidia-cufile==1.18.1.6 # via cuda-toolkit nvidia-curand==10.4.0.35 # via cuda-toolkit -nvidia-cusolver==12.0.4.66 +nvidia-cusolver==12.2.6.9 # via cuda-toolkit -nvidia-cusparse==12.6.3.3 +nvidia-cusparse==12.8.2.51 # via # cuda-toolkit # nvidia-cusolver -nvidia-cusparselt-cu13==0.8.1 +nvidia-cusparselt-cu13==0.9.1 # via torch -nvidia-nccl-cu13==2.29.7 +nvidia-nccl-cu13==2.30.7 # via torch -nvidia-nvjitlink==13.0.88 +nvidia-nvjitlink==13.3.33 # via # cuda-toolkit # nvidia-cufft # nvidia-cusolver # nvidia-cusparse -nvidia-nvshmem-cu13==3.4.5 +nvidia-nvshmem-cu13==3.7.2 # via torch -nvidia-nvtx==13.0.85 +nvidia-nvtx==13.3.29 # via cuda-toolkit open-clip-torch==2.32.0 # via -r requirements/test/cuda.in -openai==2.44.0 +openai==2.53.0 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -665,7 +665,7 @@ opencv-python-headless==4.13.0.90 # mistral-common openpyxl==3.1.5 # via -r requirements/test/cuda.in -opentelemetry-api==1.35.0 +opentelemetry-api==1.44.0 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -674,27 +674,27 @@ opentelemetry-api==1.35.0 # opentelemetry-exporter-prometheus # opentelemetry-sdk # opentelemetry-semantic-conventions -opentelemetry-exporter-otlp==1.35.0 +opentelemetry-exporter-otlp==1.44.0 # via # -c requirements/common.txt # -r requirements/test/../common.txt -opentelemetry-exporter-otlp-proto-common==1.35.0 +opentelemetry-exporter-otlp-proto-common==1.44.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http -opentelemetry-exporter-otlp-proto-grpc==1.35.0 +opentelemetry-exporter-otlp-proto-grpc==1.44.0 # via opentelemetry-exporter-otlp -opentelemetry-exporter-otlp-proto-http==1.35.0 +opentelemetry-exporter-otlp-proto-http==1.44.0 # via opentelemetry-exporter-otlp -opentelemetry-exporter-prometheus==0.56b0 +opentelemetry-exporter-prometheus==0.65b0 # via ray -opentelemetry-proto==1.35.0 +opentelemetry-proto==1.44.0 # via # opentelemetry-exporter-otlp-proto-common # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http # ray -opentelemetry-sdk==1.35.0 +opentelemetry-sdk==1.44.0 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -702,9 +702,9 @@ opentelemetry-sdk==1.35.0 # opentelemetry-exporter-otlp-proto-http # opentelemetry-exporter-prometheus # ray -opentelemetry-semantic-conventions==0.56b0 +opentelemetry-semantic-conventions==0.65b0 # via opentelemetry-sdk -opentelemetry-semantic-conventions-ai==0.4.13 +opentelemetry-semantic-conventions-ai==0.5.1 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -751,13 +751,13 @@ partial-json-parser==0.2.1.1.post7 # via -r requirements/test/../common.txt pathspec==0.12.1 # via black -pathvalidate==3.2.1 +pathvalidate==3.3.1 # via pytablewriter patsy==1.0.1 # via statsmodels -peft==0.19.1 +peft==0.20.0 # via -r requirements/test/cuda.in -perceptron==0.1.4 +perceptron==0.3.5 # via -r requirements/test/cuda.in perf-analyzer==0.1.0 # via genai-perf @@ -773,7 +773,7 @@ pillow==10.4.0 # scikit-image # segmentation-models-pytorch # torchvision -platformdirs==4.3.6 +platformdirs==4.11.1 # via # black # pooch @@ -782,34 +782,34 @@ plotly==5.24.1 # via # -r requirements/test/cuda.in # genai-perf -pluggy==1.5.0 +pluggy==1.6.0 # via # pytest # pytest-cov -polars==1.29.0 +polars==1.43.2 # via mteb -pooch==1.8.2 +pooch==1.9.0 # via librosa portalocker==2.10.1 # via sacrebleu pqdm==0.2.0 # via -r requirements/test/cuda.in -prometheus-client==0.22.0 +prometheus-client==0.26.0 # via # -c requirements/common.txt # -r requirements/test/../common.txt # opentelemetry-exporter-prometheus # prometheus-fastapi-instrumentator # ray -prometheus-fastapi-instrumentator==8.0.2 +prometheus-fastapi-instrumentator==8.1.0 # via # -c requirements/common.txt # -r requirements/test/../common.txt -propcache==0.2.0 +propcache==0.5.2 # via # aiohttp # yarl -proto-plus==1.26.1 +proto-plus==1.28.3 # via google-api-core protobuf==6.33.6 # via @@ -844,17 +844,17 @@ pyasn1==0.6.1 # rsa pyasn1-modules==0.4.2 # via google-auth -pybase64==1.4.3 +pybase64==1.5.0 # via -r requirements/test/../common.txt pycountry==24.6.1 # via pydantic-extra-types pycparser==2.22 # via cffi -pycryptodomex==3.22.0 +pycryptodomex==3.23.0 # via blobfile pycxxfilt==0.1.0 # via torch-abi-audit -pydantic==2.12.0 +pydantic==2.13.4 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -876,29 +876,29 @@ pydantic==2.12.0 # pydantic-settings # ray # xgrammar -pydantic-core==2.41.1 +pydantic-core==2.48.0 # via pydantic -pydantic-extra-types==2.10.5 +pydantic-extra-types==2.11.1 # via # fastapi # mistral-common -pydantic-settings==2.14.2 +pydantic-settings==2.15.0 # via # fastapi # mcp -pygments==2.18.0 +pygments==2.20.0 # via # pytest # rich -pyjwt==2.11.0 +pyjwt==2.13.0 # via # mcp # msal -pyparsing==3.2.0 +pyparsing==3.3.2 # via matplotlib pyrate-limiter==4.4.0 # via schemathesis -pystemmer==3.0.0 +pystemmer==3.1.0 # via mteb pytablewriter==1.2.0 # via lm-eval @@ -919,15 +919,15 @@ pytest-asyncio==1.4.0 # via -r requirements/test/cuda.in pytest-cov==6.3.0 # via -r requirements/test/cuda.in -pytest-forked==1.6.0 +pytest-forked==1.7.5 # via -r requirements/test/cuda.in -pytest-mock==3.14.0 +pytest-mock==3.15.1 # via genai-perf pytest-rerunfailures==14.0 # via -r requirements/test/cuda.in pytest-shard==0.1.2 # via -r requirements/test/cuda.in -pytest-timeout==2.3.1 +pytest-timeout==2.4.0 # via -r requirements/test/cuda.in python-dateutil==2.9.0.post0 # via @@ -945,7 +945,7 @@ python-multipart==0.0.32 # via # fastapi # mcp -python-rapidjson==1.20 +python-rapidjson==1.23 # via tritonclient pytrec-eval-terrier==0.5.7 # via mteb @@ -978,17 +978,17 @@ pyzmq==27.1.0 # via # -c requirements/common.txt # -r requirements/test/../common.txt -rapidfuzz==3.12.1 +rapidfuzz==3.14.5 # via jiwer ray==2.48.0 # via -r requirements/test/cuda.in redis==5.2.0 # via tensorizer -referencing==0.35.1 +referencing==0.37.0 # via # jsonschema # jsonschema-specifications -regex==2026.2.28 +regex==2026.7.19 # via # -r requirements/test/../common.txt # nltk @@ -996,7 +996,7 @@ regex==2026.2.28 # sacrebleu # tiktoken # transformers -requests==2.32.3 +requests==2.34.2 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -1019,7 +1019,7 @@ requests==2.32.3 # schemathesis # starlette-testclient # tiktoken -responses==0.25.3 +responses==0.26.2 # via genai-perf rich==13.9.4 # via @@ -1033,7 +1033,7 @@ rich-toolkit==0.20.1 # via # fastapi-cli # fastapi-cloud-cli -rignore==0.7.6 +rignore==0.8.1 # via fastapi-cloud-cli rouge-score==0.1.2 # via lm-eval @@ -1043,17 +1043,17 @@ rpds-py==0.20.1 # referencing rsa==4.9.1 # via google-auth -runai-model-streamer==0.15.7 +runai-model-streamer==0.16.1 # via -r requirements/test/cuda.in -runai-model-streamer-azure==0.15.7 +runai-model-streamer-azure==0.16.1 # via runai-model-streamer -runai-model-streamer-gcs==0.15.7 +runai-model-streamer-gcs==0.16.1 # via runai-model-streamer -runai-model-streamer-s3==0.15.7 +runai-model-streamer-s3==0.16.1 # via runai-model-streamer -s3transfer==0.10.3 +s3transfer==0.19.2 # via boto3 -sacrebleu==2.4.3 +sacrebleu==2.6.0 # via lm-eval safetensors==0.8.0 # via @@ -1065,18 +1065,18 @@ safetensors==0.8.0 # segmentation-models-pytorch # timm # transformers -schemathesis==4.21.6 +schemathesis==4.24.3 # via -r requirements/test/cuda.in scikit-image==0.25.2 # via albumentations -scikit-learn==1.5.2 +scikit-learn==1.7.2 # via # albumentations # librosa # lm-eval # mteb # sentence-transformers -scipy==1.13.1 +scipy==1.15.3 # via # albumentations # bm25s @@ -1090,13 +1090,13 @@ scipy==1.13.1 # vocos segmentation-models-pytorch==0.5.0 # via -r requirements/test/cuda.in -sentence-transformers==5.2.0 +sentence-transformers==5.7.0 # via # -r requirements/test/cuda.in # mteb sentencepiece==0.2.1 # via -r requirements/test/../common.txt -sentry-sdk==2.63.0 +sentry-sdk==2.66.1 # via fastapi-cloud-cli setproctitle==1.3.7 # via -r requirements/test/../common.txt @@ -1111,7 +1111,7 @@ shellingham==1.5.4 # via # perceptron # typer -six==1.16.0 +six==1.17.0 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -1128,7 +1128,7 @@ sniffio==1.3.1 # openai sortedcontainers==2.4.0 # via hypothesis -soundfile==0.12.1 +soundfile==0.14.0 # via # -r requirements/test/cuda.in # genai-perf @@ -1146,7 +1146,7 @@ sqlitedict==2.1.0 # via lm-eval sse-starlette==3.4.5 # via mcp -starlette==1.3.1 +starlette==1.5.1 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -1164,15 +1164,15 @@ structlog==25.4.0 # via gpt-oss supervisor==4.3.0 # via model-hosting-container-standards -sympy==1.13.3 +sympy==1.14.0 # via # einx # torch tabledata==1.3.3 # via pytablewriter -tabulate==0.9.0 +tabulate==0.10.0 # via sacrebleu -tblib==3.1.0 +tblib==3.2.2 # via -r requirements/test/cuda.in tcolorpy==0.1.6 # via pytablewriter @@ -1182,15 +1182,15 @@ tenacity==9.1.2 # lm-eval # plotly # schemathesis -tensorizer==2.10.1 +tensorizer==2.12.1 # via -r requirements/test/cuda.in -termcolor==3.1.0 +termcolor==3.3.0 # via gpt-oss -threadpoolctl==3.5.0 +threadpoolctl==3.6.0 # via scikit-learn tifffile==2025.3.30 # via scikit-image -tiktoken==0.12.0 +tiktoken==0.13.0 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -1202,7 +1202,7 @@ timm==1.0.17 # -r requirements/test/cuda.in # open-clip-torch # segmentation-models-pytorch -tokenizers==0.22.2 +tokenizers==0.23.1 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -1237,7 +1237,7 @@ torchaudio==2.11.0+cu130 # -r requirements/test/cuda.in # encodec # vocos -torchcodec==0.14.0+cu130 +torchcodec==0.15.0 # via # -c requirements/cuda.txt # -r requirements/test/cuda.in @@ -1248,7 +1248,7 @@ torchvision==0.28.0+cu130 # open-clip-torch # segmentation-models-pytorch # timm -tqdm==4.67.3 +tqdm==4.70.0 # via # -r requirements/test/../common.txt # datasets @@ -1282,21 +1282,21 @@ triton==3.7.1 # via # torch # xgrammar -tritonclient==2.64.0 +tritonclient==2.71.0 # via -r requirements/test/cuda.in typepy==1.3.2 # via # dataproperty # pytablewriter # tabledata -typer==0.26.8 +typer==0.27.1 # via # fastapi-cli # fastapi-cloud-cli # fastsafetensors # perceptron # transformers -typing-extensions==4.15.0 +typing-extensions==4.16.0 # via # -c requirements/common.txt # -r requirements/test/../common.txt @@ -1345,7 +1345,7 @@ typing-inspection==0.4.2 # pydantic-settings tzdata==2024.2 # via pandas -urllib3==2.2.3 +urllib3==2.7.0 # via # blobfile # botocore @@ -1354,7 +1354,7 @@ urllib3==2.2.3 # responses # sentry-sdk # tritonclient -uvicorn==0.35.0 +uvicorn==0.52.1 # via # fastapi # fastapi-cli @@ -1363,7 +1363,7 @@ uvicorn==0.35.0 # mcp uvloop==0.22.1 # via uvicorn -vector-quantize-pytorch==1.21.2 +vector-quantize-pytorch==1.31.1 # via -r requirements/test/cuda.in virtualenv==20.31.2 # via ray @@ -1373,7 +1373,7 @@ watchfiles==1.2.0 # via # -r requirements/test/../common.txt # uvicorn -wcwidth==0.2.13 +wcwidth==0.8.2 # via ftfy websockets==16.0 # via uvicorn @@ -1387,11 +1387,11 @@ xgrammar==0.2.3 # via # -c requirements/common.txt # -r requirements/test/../common.txt -xxhash==3.5.0 +xxhash==3.8.1 # via # datasets # evaluate -yarl==1.17.1 +yarl==1.24.5 # via aiohttp zipp==3.23.0 # via importlib-metadata diff --git a/requirements/xpu.txt b/requirements/xpu.txt index dc81cce64f..35b66beb8f 100644 --- a/requirements/xpu.txt +++ b/requirements/xpu.txt @@ -10,12 +10,12 @@ setuptools>=77.0.3,<81.0.0 wheel jinja2>=3.1.6 datasets # for benchmark scripts -numba == 0.65.0 # Required for N-gram speculative decoding +numba == 0.66.0 # Required for N-gram speculative decoding --extra-index-url=https://download.pytorch.org/whl/xpu torch==2.13.0 torchaudio torchvision -torchcodec >= 0.14 # Required for the torchcodec video decoding backend +torchcodec >= 0.15.0 # Required for the torchcodec video decoding backend auto_round_lib==0.14.2 vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.12/vllm_xpu_kernels-0.1.12-cp38-abi3-manylinux_2_28_x86_64.whl diff --git a/setup.py b/setup.py index e29548af67..6416955c7d 100644 --- a/setup.py +++ b/setup.py @@ -1275,9 +1275,9 @@ def add_vllm_package_data(filename: str) -> None: install_requires=get_requirements(), extras_require={ # AMD Zen CPU optimizations via zentorch - "zen": ["zentorch==2.11.0.0"], + "zen": ["zentorch==2.13.0.0"], "bench": ["pandas", "matplotlib", "seaborn", "datasets", "scipy", "plotly"], - "tensorizer": ["tensorizer==2.10.1"], + "tensorizer": ["tensorizer==2.12.1"], "fastsafetensors": ["fastsafetensors >= 0.3.2"], "instanttensor": ["instanttensor >= 0.1.9"], "runai": ["runai-model-streamer[s3,gcs,azure] >= 0.15.7"],