From 4e10641d699ee228a37806f01511e1bc70150d55 Mon Sep 17 00:00:00 2001 From: pandyamarut Date: Tue, 19 Nov 2024 12:14:04 -0800 Subject: [PATCH] update vllm Signed-off-by: pandyamarut --- Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Dockerfile b/Dockerfile index 0a08a18..752273b 100644 --- a/Dockerfile +++ b/Dockerfile @@ -12,7 +12,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \ python3 -m pip install --upgrade -r /requirements.txt # Install vLLM (switching back to pip installs since issues that required building fork are fixed and space optimization is not as important since caching) and FlashInfer -RUN python3 -m pip install vllm==0.6.3 && \ +RUN python3 -m pip install vllm==0.6.4 && \ python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3 # Setup for Option 2: Building the Image with the Model included