caddfa31434
Results
2
comments of
caddfa31434
I noticed there's a feature request related to Medusa/Eagle at https://github.com/vllm-project/vllm/issues/4669
Try to build vllm from source using the nvcr.io/nvidia/pytorch:24.04-py3 container to avoid the bug related to cuBLAS on specific shapes (on H20).