[Dependencies] Upgrade transformers to >= 5.5.0 and compressed-tensors to >= 0.15.0

Upgrade transformers from >= 4.56.0, < 5 to >= 5.5.0 and compressed-tensors
from == 0.14.0.1 to >= 0.15.0. Also bump tokenizers to 0.22.2 and
huggingface-hub to 1.9.2 to satisfy transformers 5.x dependency requirements.
Regenerate all lockfiles (test.txt, rocm-test.txt, xpu-test.txt).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

requirements/common.txt

@@ -7,7 +7,7 @@ requests >= 2.26.0
 tqdm
 blake3
 py-cpuinfo
-transformers >= 4.56.0, < 5
+transformers >= 5.5.0
 tokenizers >= 0.21.1  # Required for fast incremental detokenization.
 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] >= 0.115.0 # Required by FastAPI's form models in the OpenAI API server's audio transcriptions endpoint.
@@ -37,7 +37,7 @@ pyyaml
 six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
 setuptools>=77.0.3,<81.0.0; python_version > '3.11' # Setuptools is used by triton, we need to ensure a modern version is installed for 3.12+ so that it does not try to import distutils, which was removed in 3.12
 einops # Required for Qwen2-VL.
-compressed-tensors == 0.14.0.1 # required for compressed-tensors
+compressed-tensors >= 0.15.0 # required for compressed-tensors
 depyf==0.20.0 # required for profiling and debugging with compilation config
 cloudpickle # allows pickling lambda functions in model_executor/models/registry.py
 watchfiles # required for http server to monitor the updates of TLS files

requirements/nightly_torch_test.txt

@@ -29,8 +29,8 @@ opencv-python-headless >= 4.13.0 # required for video test
 datamodel_code_generator # required for minicpm3 test
 lm-eval[api]>=0.4.11 # required for model evaluation test
 mteb[bm25s]>=2, <3 # required for mteb test
-transformers==4.57.5
-tokenizers==0.22.0
+transformers==5.5.0
+tokenizers==0.22.2
 schemathesis>=3.39.15 # Required for openai schema test.
 # quantization
 bitsandbytes>=0.49.2

requirements/rocm-test.in

@@ -38,8 +38,8 @@ opencv-python-headless>=4.13.0 # required for video test
 datamodel_code_generator # required for minicpm3 test
 lm-eval[api]>=0.4.11 # required for model evaluation test
 mteb[bm25s]>=2, <3 # required for mteb test
-transformers==4.57.5
-tokenizers==0.22.0
+transformers==5.5.0
+tokenizers==0.22.2
 schemathesis>=3.39.15 # Required for openai schema test
 # quantization
 bitsandbytes==0.49.2
@@ -82,4 +82,4 @@ plotly # required for perf comparison html report
 rapidfuzz
 torchgeo==0.7.0
 multiprocess==0.70.16
-huggingface-hub==0.36.2
+huggingface-hub==1.9.2

requirements/rocm-test.txt

@@ -172,7 +172,7 @@ colorful==0.5.8
     # via ray
 colorlog==6.10.1
     # via optuna
-compressed-tensors==0.14.0.1
+compressed-tensors==0.15.0
     # via
     #   -c requirements/common.txt
     #   -r requirements/common.txt
@@ -288,7 +288,6 @@ filelock==3.25.2
     #   python-discovery
     #   ray
     #   torch
-    #   transformers
     #   virtualenv
 fiona==1.10.1
     # via torchgeo
@@ -382,7 +381,7 @@ h5py==3.16.0
     # via terratorch
 harfile==0.4.0
     # via schemathesis
-hf-xet==1.4.2
+hf-xet==1.4.3
     # via huggingface-hub
 hiredis==3.3.1
     # via tensorizer
@@ -401,6 +400,7 @@ httpx==0.27.2
     #   diffusers
     #   fastapi
     #   fastapi-cloud-cli
+    #   huggingface-hub
     #   mcp
     #   model-hosting-container-standards
     #   openai
@@ -408,7 +408,7 @@ httpx==0.27.2
     #   schemathesis
 httpx-sse==0.4.3
     # via mcp
-huggingface-hub==0.36.2
+huggingface-hub==1.9.2
     # via
     #   -r requirements/rocm-test.in
     #   accelerate
@@ -734,6 +734,45 @@ numpy==2.2.6
     #   vocos
     #   xarray
     #   xgrammar
+nvidia-cublas-cu12==12.8.4.1
+    # via
+    #   nvidia-cudnn-cu12
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cuda-cupti-cu12==12.8.90
+    # via torch
+nvidia-cuda-nvrtc-cu12==12.8.93
+    # via torch
+nvidia-cuda-runtime-cu12==12.8.90
+    # via torch
+nvidia-cudnn-cu12==9.10.2.21
+    # via torch
+nvidia-cufft-cu12==11.3.3.83
+    # via torch
+nvidia-cufile-cu12==1.13.1.3
+    # via torch
+nvidia-curand-cu12==10.3.9.90
+    # via torch
+nvidia-cusolver-cu12==11.7.3.90
+    # via torch
+nvidia-cusparse-cu12==12.5.8.93
+    # via
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cusparselt-cu12==0.7.1
+    # via torch
+nvidia-nccl-cu12==2.27.5
+    # via torch
+nvidia-nvjitlink-cu12==12.8.93
+    # via
+    #   nvidia-cufft-cu12
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+    #   torch
+nvidia-nvshmem-cu12==3.4.5
+    # via torch
+nvidia-nvtx-cu12==12.8.90
+    # via torch
 omegaconf==2.3.0
     # via
     #   hydra-core
@@ -1178,7 +1217,6 @@ requests==2.32.5
     #   google-api-core
     #   google-cloud-storage
     #   gpt-oss
-    #   huggingface-hub
     #   lightly
     #   lm-eval
     #   mistral-common
@@ -1192,7 +1230,6 @@ requests==2.32.5
     #   starlette-testclient
     #   tacoreader
     #   tiktoken
-    #   transformers
     #   wandb
 resampy==0.4.3
     # via -r requirements/rocm-test.in
@@ -1426,7 +1463,7 @@ timm==1.0.17
     #   segmentation-models-pytorch
     #   terratorch
     #   torchgeo
-tokenizers==0.22.0
+tokenizers==0.22.2
     # via
     #   -c requirements/common.txt
     #   -r requirements/common.txt
@@ -1469,7 +1506,7 @@ tqdm==4.67.3
     #   tacoreader
     #   terratorch
     #   transformers
-transformers==4.57.5
+transformers==5.5.0
     # via
     #   -c requirements/common.txt
     #   -r requirements/common.txt
@@ -1496,7 +1533,9 @@ typer==0.24.1
     #   fastapi-cli
     #   fastapi-cloud-cli
     #   fastsafetensors
+    #   huggingface-hub
     #   perceptron
+    #   transformers
 typeshed-client==2.9.0
     # via jsonargparse
 typing-extensions==4.15.0
@@ -1626,20 +1665,4 @@ zstandard==0.25.0
 # triton
 # cuda-bindings
 # cuda-pathfinder
-# cuda-toolkit
 # cupy-cuda12x
-# nvidia-cublas
-# nvidia-cuda-cupti
-# nvidia-cuda-nvrtc
-# nvidia-cuda-runtime
-# nvidia-cudnn-cu13
-# nvidia-cufft
-# nvidia-cufile
-# nvidia-curand
-# nvidia-cusolver
-# nvidia-cusparse
-# nvidia-cusparselt-cu13
-# nvidia-nccl-cu13
-# nvidia-nvjitlink
-# nvidia-nvshmem-cu13
-# nvidia-nvtx

requirements/test.in

@@ -39,8 +39,8 @@ opencv-python-headless >= 4.13.0 # required for video test
 datamodel_code_generator # required for minicpm3 test
 lm-eval[api]>=0.4.11 # required for model evaluation test
 mteb[bm25s]>=2, <3 # required for mteb test
-transformers==4.57.5
-tokenizers==0.22.0
+transformers==5.5.0
+tokenizers==0.22.2
 schemathesis>=3.39.15 # Required for openai schema test.
 # quantization
 bitsandbytes==0.49.2

requirements/test.txt

@@ -246,7 +246,6 @@ filelock==3.16.1
     #   huggingface-hub
     #   ray
     #   torch
-    #   transformers
     #   virtualenv
 fiona==1.10.1
     # via torchgeo
@@ -329,7 +328,7 @@ h5py==3.13.0
     # via terratorch
 harfile==0.3.0
     # via schemathesis
-hf-xet==1.1.7
+hf-xet==1.4.3
     # via huggingface-hub
 hiredis==3.0.0
     # via tensorizer
@@ -343,9 +342,10 @@ httpx==0.27.2
     # via
     #   -r requirements/test.in
     #   diffusers
+    #   huggingface-hub
     #   perceptron
     #   schemathesis
-huggingface-hub==0.36.2
+huggingface-hub==1.9.2
     # via
     #   accelerate
     #   datasets
@@ -979,7 +979,7 @@ referencing==0.35.1
     # via
     #   jsonschema
     #   jsonschema-specifications
-regex==2024.9.11
+regex==2026.4.4
     # via
     #   diffusers
     #   nltk
@@ -999,7 +999,6 @@ requests==2.32.3
     #   google-api-core
     #   google-cloud-storage
     #   gpt-oss
-    #   huggingface-hub
     #   lightly
     #   lm-eval
     #   mistral-common
@@ -1012,7 +1011,6 @@ requests==2.32.3
     #   starlette-testclient
     #   tacoreader
     #   tiktoken
-    #   transformers
     #   wandb
 resampy==0.4.3
     # via -r requirements/test.in
@@ -1213,7 +1211,7 @@ timm==1.0.17
     #   segmentation-models-pytorch
     #   terratorch
     #   torchgeo
-tokenizers==0.22.0
+tokenizers==0.22.2
     # via
     #   -c requirements/common.txt
     #   -r requirements/test.in
@@ -1289,7 +1287,7 @@ tqdm==4.67.3
     #   tacoreader
     #   terratorch
     #   transformers
-transformers==4.57.5
+transformers==5.5.0
     # via
     #   -c requirements/common.txt
     #   -r requirements/test.in
@@ -1311,7 +1309,9 @@ typepy==1.3.2
 typer==0.15.2
     # via
     #   fastsafetensors
+    #   huggingface-hub
     #   perceptron
+    #   transformers
 types-python-dateutil==2.9.0.20241206
     # via arrow
 typeshed-client==2.8.2

requirements/xpu-test.txt

@@ -1,5 +1,5 @@
 # This file was autogenerated by uv via the following command:
-#    uv pip compile requirements/xpu-test.in -o requirements/xpu-test.txt -c requirements/xpu.txt --python-version 3.12 --index-strategy unsafe-best-match
+#    uv pip compile requirements/xpu-test.in -o requirements/xpu-test.txt -c requirements/xpu.txt --python-version 3.12 --index-strategy unsafe-best-match --python-platform x86_64-manylinux_2_28
 absl-py==2.4.0
     # via
     #   -r requirements/xpu-test.in
@@ -19,7 +19,9 @@ aiosignal==1.4.0
 albumentations==1.4.6
     # via -r requirements/xpu-test.in
 annotated-doc==0.0.4
-    # via fastapi
+    # via
+    #   fastapi
+    #   typer
 annotated-types==0.7.0
     # via pydantic
 anyio==4.13.0
@@ -64,6 +66,7 @@ click==8.3.1
     #   jiwer
     #   nltk
     #   schemathesis
+    #   typer
     #   uvicorn
 colorama==0.4.6
     # via sacrebleu
@@ -90,7 +93,7 @@ docker==7.1.0
     # via gpt-oss
 docopt==0.6.2
     # via num2words
-dpcpp-cpp-rt==2025.3.1
+dpcpp-cpp-rt==2025.3.2
     # via
     #   onemkl-sycl-blas
     #   onemkl-sycl-dft
@@ -112,7 +115,6 @@ filelock==3.25.2
     #   huggingface-hub
     #   modelscope
     #   torch
-    #   transformers
 frozenlist==1.8.0
     # via
     #   aiohttp
@@ -135,7 +137,7 @@ harfile==0.4.0
     # via schemathesis
 hf-transfer==0.1.9
     # via -r requirements/xpu-test.in
-hf-xet==1.4.2
+hf-xet==1.4.3
     # via huggingface-hub
 html2text==2025.4.15
     # via gpt-oss
@@ -144,8 +146,9 @@ httpcore==1.0.9
 httpx==0.28.1
     # via
     #   datasets
+    #   huggingface-hub
     #   schemathesis
-huggingface-hub==0.36.2
+huggingface-hub==1.9.2
     # via
     #   accelerate
     #   datasets
@@ -171,27 +174,27 @@ idna==3.11
     #   yarl
 imageio==2.37.3
     # via scikit-image
-impi-rt==2021.17.0
+impi-rt==2021.17.2
     # via
     #   oneccl
     #   torch
 iniconfig==2.3.0
     # via pytest
-intel-cmplr-lib-rt==2025.3.1
+intel-cmplr-lib-rt==2025.3.2
     # via
     #   intel-sycl-rt
     #   torch
-intel-cmplr-lib-ur==2025.3.1
+intel-cmplr-lib-ur==2025.3.2
     # via
     #   intel-openmp
     #   intel-sycl-rt
     #   torch
-intel-cmplr-lic-rt==2025.3.1
+intel-cmplr-lic-rt==2025.3.2
     # via
     #   intel-opencl-rt
     #   intel-sycl-rt
     #   torch
-intel-opencl-rt==2025.3.1
+intel-opencl-rt==2025.3.2
     # via
     #   dpcpp-cpp-rt
     #   onemkl-sycl-blas
@@ -200,14 +203,14 @@ intel-opencl-rt==2025.3.1
     #   onemkl-sycl-rng
     #   onemkl-sycl-sparse
     #   torch
-intel-openmp==2025.3.1
+intel-openmp==2025.3.2
     # via
     #   dpcpp-cpp-rt
     #   mkl
     #   torch
-intel-pti==0.15.0
+intel-pti==0.16.0
     # via torch
-intel-sycl-rt==2025.3.1
+intel-sycl-rt==2025.3.2
     # via
     #   dpcpp-cpp-rt
     #   oneccl
@@ -265,11 +268,11 @@ mbstrdecoder==1.1.4
     #   typepy
 mdurl==0.1.2
     # via markdown-it-py
-mistral-common==1.10.0
+mistral-common==1.11.0
     # via
     #   -c requirements/common.txt
     #   -r requirements/xpu-test.in
-mkl==2025.3.0
+mkl==2025.3.1
     # via
     #   onemkl-sycl-blas
     #   onemkl-sycl-dft
@@ -334,28 +337,28 @@ numpy==2.2.6
     #   tifffile
     #   torchvision
     #   transformers
-oneccl==2021.17.1
+oneccl==2021.17.2
     # via
     #   oneccl-devel
     #   torch
-oneccl-devel==2021.17.1
+oneccl-devel==2021.17.2
     # via torch
-onemkl-license==2025.3.0
+onemkl-license==2025.3.1
     # via
     #   mkl
     #   torch
-onemkl-sycl-blas==2025.3.0
+onemkl-sycl-blas==2025.3.1
     # via
     #   onemkl-sycl-lapack
     #   onemkl-sycl-sparse
     #   torch
-onemkl-sycl-dft==2025.3.0
+onemkl-sycl-dft==2025.3.1
     # via torch
-onemkl-sycl-lapack==2025.3.0
+onemkl-sycl-lapack==2025.3.1
     # via torch
-onemkl-sycl-rng==2025.3.0
+onemkl-sycl-rng==2025.3.1
     # via torch
-onemkl-sycl-sparse==2025.3.0
+onemkl-sycl-sparse==2025.3.1
     # via torch
 openai-harmony==0.0.8
     # via
@@ -515,7 +518,6 @@ requests==2.33.1
     #   docker
     #   evaluate
     #   gpt-oss
-    #   huggingface-hub
     #   lm-eval
     #   mistral-common
     #   modelscope
@@ -524,11 +526,11 @@ requests==2.33.1
     #   schemathesis
     #   starlette-testclient
     #   tiktoken
-    #   transformers
 rich==14.3.3
     # via
     #   mteb
     #   schemathesis
+    #   typer
 rouge-score==0.1.2
     # via lm-eval
 rpds-py==0.30.0
@@ -572,6 +574,8 @@ setuptools==80.10.2
     #   modelscope
     #   pytablewriter
     #   torch
+shellingham==1.5.4
+    # via typer
 six==1.17.0
     # via
     #   -c requirements/common.txt
@@ -606,7 +610,7 @@ tabledata==1.3.4
     # via pytablewriter
 tabulate==0.10.0
     # via sacrebleu
-tbb==2022.3.0
+tbb==2022.3.1
     # via
     #   intel-opencl-rt
     #   mkl
@@ -643,7 +647,7 @@ tokenizers==0.22.2
     # via
     #   -c requirements/common.txt
     #   transformers
-torch==2.10.0+xpu
+torch==2.11.0+xpu
     # via
     #   -c requirements/xpu.txt
     #   accelerate
@@ -651,7 +655,7 @@ torch==2.10.0+xpu
     #   sentence-transformers
     #   timm
     #   torchvision
-torchvision==0.25.0+xpu
+torchvision==0.26.0+xpu
     # via timm
 tqdm==4.67.3
     # via
@@ -665,17 +669,21 @@ tqdm==4.67.3
     #   pqdm
     #   sentence-transformers
     #   transformers
-transformers==4.57.6
+transformers==5.5.0
     # via
     #   -c requirements/common.txt
     #   sentence-transformers
-triton-xpu==3.6.0
+triton-xpu==3.7.0
     # via torch
 typepy==1.3.4
     # via
     #   dataproperty
     #   pytablewriter
     #   tabledata
+typer==0.24.1
+    # via
+    #   huggingface-hub
+    #   transformers
 typing-extensions==4.15.0
     # via
     #   -c requirements/common.txt
@@ -704,7 +712,7 @@ typing-inspection==0.4.2
     # via
     #   fastapi
     #   pydantic
-umf==1.0.2
+umf==1.0.3
     # via
     #   intel-cmplr-lib-ur
     #   torch