update vllm

Signed-off-by: pandyamarut <pandyamarut@gmail.com>
2025-04-21 13:14:32 -07:00
parent 6b64bb93bd
commit f33e8d2bcd
4 changed files with 66 additions and 5 deletions
@@ -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==0.8.3 && \
+RUN python3 -m pip install vllm==0.8.4 && \
    python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3

 # Setup for Option 2: Building the Image with the Model included