Bump the minor-update group across 1 directory with 178 updates

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

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"

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

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

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