From 58bfe62e93aeb22675702bd463a9e45d07d03e98 Mon Sep 17 00:00:00 2001 From: "yuze.zyz" Date: Wed, 18 Sep 2024 16:34:44 +0800 Subject: [PATCH] update vllm version to 0.6.0 --- docker/Dockerfile.ubuntu | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docker/Dockerfile.ubuntu b/docker/Dockerfile.ubuntu index ed7c0cba..8aadb8c9 100644 --- a/docker/Dockerfile.ubuntu +++ b/docker/Dockerfile.ubuntu @@ -58,7 +58,8 @@ RUN if [ "$USE_GPU" = "True" ] ; then \ pip install --no-cache-dir -U 'xformers<0.0.27' --index-url https://download.pytorch.org/whl/cu121 && \ pip install --no-cache-dir --force tinycudann==1.7 -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html && \ 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 'vllm==0.5.1' https://modelscope.oss-cn-beijing.aliyuncs.com/packages/lmdeploy-0.5.0-cp310-cp310-linux_x86_64.whl; \ + pip install --no-cache-dir -U triton https://modelscope.oss-cn-beijing.aliyuncs.com/packages/lmdeploy-0.5.0-cp310-cp310-linux_x86_64.whl \ + pip install --no-cache-dir 'vllm==0.6.0'; \ else \ echo 'cpu unsupport vllm auto-gptq'; \ fi