From 436214bb7240787f8a36affa3f71687a3d0a6ff5 Mon Sep 17 00:00:00 2001
From: biondizzle <biondizzle@gmail.com>
Date: Thu, 2 Apr 2026 23:58:20 +0000
Subject: [PATCH] Use PyPI triton wheel instead of building (QEMU segfaults)

Triton 3.6.0 has official aarch64 wheel on PyPI.
Building triton from source causes segfaults under QEMU emulation.
---
 vllm/Dockerfile | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/vllm/Dockerfile b/vllm/Dockerfile
index b49a74c..6cf4a54 100644
--- a/vllm/Dockerfile
+++ b/vllm/Dockerfile
@@ -64,16 +64,10 @@ RUN mkdir /wheels
 # Pin setuptools to <81 for LMCache compatibility (needs >=77.0.3,<81.0.0)
 RUN uv pip install -U build cmake ninja pybind11 "setuptools>=77.0.3,<81.0.0" wheel
 
+# Use PyPI triton wheel instead of building (QEMU segfaults during triton build)
 FROM build-base AS build-triton
-ARG TRITON_REF=release/3.5.x
-ARG TRITON_BUILD_SUFFIX=+cu130
-ENV TRITON_WHEEL_VERSION_SUFFIX=${TRITON_BUILD_SUFFIX:-}
-RUN git clone https://github.com/triton-lang/triton.git
-RUN cd triton && \
-    git checkout ${TRITON_REF} && \
-    git submodule sync && \
-    git submodule update --init --recursive -j 8 && \
-    uv build --wheel --no-build-isolation -o /wheels
+RUN mkdir -p /wheels && \
+    pip download triton==3.6.0 --platform manylinux_2_27_aarch64 --only-binary=:all: --no-deps -d /wheels
 
 FROM build-base AS build-xformers
 #ARG XFORMERS_REF=v0.0.32.post2