This commit is contained in:
Jintao Huang
2024-11-08 20:53:59 +08:00
parent 7d4c26fd2b
commit 633d879fcf

View File

@@ -7,7 +7,7 @@ vllm_version=${4:-0.6.0}
lmdeploy_version=${5:-0.6.1}
autogptq_version=${6:-0.7.1}
pip install --no-cache-dir -U autoawq
pip install --no-cache-dir -U autoawq lmdeploy==$lmdeploy_version
pip uninstall -y torch torchvision torchaudio
@@ -19,12 +19,6 @@ pip install --no-cache-dir tiktoken transformers_stream_generator bitsandbytes d
# find on: https://github.com/Dao-AILab/flash-attention/releases
cd /tmp && git clone https://github.com/Dao-AILab/flash-attention.git && cd flash-attention && python setup.py install && cd / && rm -fr /tmp/flash-attention && pip cache purge;
pip install --no-cache-dir auto-gptq==$autogptq_version
pip install --no-cache-dir triton auto-gptq==$autogptq_version vllm==$vllm_version -U && pip cache purge
# pip uninstall -y torch-scatter && TORCH_CUDA_ARCH_LIST="6.0;6.1;6.2;7.0;7.5;8.0;8.6;8.9;9.0" pip install --no-cache-dir -U torch-scatter
pip install --no-cache-dir -U triton
pip install --no-cache-dir vllm==$vllm_version -U
pip install --no-cache-dir -U lmdeploy==$lmdeploy_version