From 14467bef70ac62823aab68ee2e776e6ace017268 Mon Sep 17 00:00:00 2001
From: biondizzle <biondizzle@gmail.com>
Date: Thu, 2 Apr 2026 20:55:32 +0000
Subject: [PATCH] Fix: add --no-build-isolation to pip wheel for
 flash-attention

Without this flag, pip runs the build in an isolated environment
that doesn't have access to torch in the venv.
---
 vllm/Dockerfile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/vllm/Dockerfile b/vllm/Dockerfile
index 642e9cf..ee680b1 100644
--- a/vllm/Dockerfile
+++ b/vllm/Dockerfile
@@ -122,7 +122,7 @@ RUN apt-get update && apt-get install -y build-essential cmake gcc && \
     FLASH_ATTENTION_FORCE_BUILD="TRUE" \
     FLASH_ATTENTION_FORCE_CXX11_ABI="FALSE" \
     FLASH_ATTENTION_SKIP_CUDA_BUILD="FALSE" \
-    pip wheel . -v --no-deps -w ./wheels/ && \
+    pip wheel . -v --no-deps --no-build-isolation -w ./wheels/ && \
     cp wheels/*.whl /wheels/
 
 FROM build-base AS build-vllm