biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc] Add developer guide for CustomOp (#30886)

Browse Source 
Signed-off-by: shen-shanshan <467638484@qq.com>
This commit is contained in:
Shanshan Shen
2026-01-10 00:21:11 +08:00
committed by GitHub
parent ac9f9330e6
commit 08d954f036
24 changed files with 441 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/config/compilation.py
View File

@@ -404,7 +404,8 @@ class CompilationConfig:
- 'none,+op1,+op2' to enable only op1 and op2
By default, all custom ops are enabled when running without Inductor and
disabled when running with Inductor: mode>=VLLM_COMPILE and backend="inductor".
disabled when running with Inductor: mode>CompilationMode.NONE and
backend="inductor".
Inductor generates (fused) Triton kernels for disabled custom ops."""
splitting_ops: list[str] | None = None
"""A list of ops to exclude from cudagraphs, used in piecewise compilation.