From 2c903bc7acf709deea8b2275a5fdf8d714dba121 Mon Sep 17 00:00:00 2001 From: Mengqing Cao Date: Fri, 18 Apr 2025 15:35:10 +0800 Subject: [PATCH] [Doc] Update doc for custom ops build (#570) - update doc about custom ops compile --------- Signed-off-by: MengqingCao --- docs/source/installation.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/source/installation.md b/docs/source/installation.md index a1e6892..93c13a6 100644 --- a/docs/source/installation.md +++ b/docs/source/installation.md @@ -178,6 +178,7 @@ pip install -e . --extra-index https://download.pytorch.org/whl/cpu/ ```{note} vllm-ascend will build custom ops by default. If you don't want to build it, set `COMPILE_CUSTOM_KERNELS=0` environment to disable it. +To build custom ops, gcc/g++ higher than 8 and c++ 17 or higher is required. If you encourage a torch-npu version conflict, please install with `pip install --no-build-isolation -e .` to build on system env. ``` ::::