vllm/requirements/rocm.txt
Daifeng Li fa78de9dc3
Quantization: support FP4 quantized models on AMD CDNA2/CDNA3 GPUs (#22527)
Signed-off-by: feng <fengli1702@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
2025-08-22 20:53:21 -06:00

20 lines
456 B
Plaintext

# Common dependencies
-r common.txt
numba == 0.60.0; python_version == '3.9' # v0.61 doesn't support Python 3.9. Required for N-gram speculative decoding
numba == 0.61.2; python_version > '3.9'
# Dependencies for AMD GPUs
boto3
botocore
datasets
ray>=2.10.0,<2.45.0
peft
pytest-asyncio
tensorizer==2.10.1
packaging>=24.2
setuptools>=77.0.3,<80.0.0
setuptools-scm>=8
runai-model-streamer==0.11.0
runai-model-streamer-s3==0.11.0
conch-triton-kernels==1.2.1