Update installation instructions to prevent/resolve nccl error, updat…

…e poetry lock to vllm 0.4.2, update flash attention instructions for vllm 0.4.2
VectorInstitute · May 23, 2024 · 9e532c4 · 9e532c4
1 parent 3ec9069
commit 9e532c4
Show file tree

Hide file tree

Showing 3 changed files with 198 additions and 57 deletions.
diff --git a/README.md b/README.md
@@ -23,6 +23,7 @@ pip install wheel
 export CUDA_HOME=/pkgs/cuda-12.3
 
 pip install flash-attn --no-build-isolation
+pip install vllm-flash-attn
 ```
 
 ## Launch an inference server