diff --git a/serving/docker/requirements-vllm.txt b/serving/docker/requirements-vllm.txt index 0c5ace26d..3e3a8f428 100644 --- a/serving/docker/requirements-vllm.txt +++ b/serving/docker/requirements-vllm.txt @@ -1,3 +1,4 @@ peft==0.14.0 llmcompressor==0.4.0 vllm==0.7.1 +https://github.com/flashinfer-ai/flashinfer/releases/download/v0.2.0.post2/flashinfer_python-0.2.0.post2+cu124torch2.5-cp311-cp311-linux_x86_64.whl