[BugFix][Fusion] Fix graph fusion failure problem (#5676)

Currently, the vllm pull request
(https://github.com/vllm-project/vllm/pull/24252) is causing operator
fusion to fail. This issue was previously fixed by patching the backend.
The root cause has been identified, and the problem can be resolved with
this pull request.
- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef

---------

Signed-off-by: wxsIcey <1790571317@qq.com>
This commit is contained in:
Icey
2026-01-07 18:42:55 +08:00
committed by GitHub
parent 137f28341d
commit b94fc13d3f
8 changed files with 37 additions and 265 deletions

View File

@@ -106,20 +106,6 @@
# Future Plan:
# Remove this patch when vLLM merge the PR.
#
# ** 7. File: platform/patch_compile_backend.py**
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# 1. `vllm.compilation.backends.PiecewiseCompileInterpreter`
# `vllm.compilation.piecewise_backend.PiecewiseBackend`
# Why:
# vllm removed the compile graph for general shape, which caused operator fusion to fail.
# This issue affects the performance of model inference on Ascend.
# How
# recover the compiled graph for dynamic_shape in PiecewiseBackend.
# Related PR (if no, explain why):
# https://github.com/vllm-project/vllm/pull/24252
# Future Plan:
# Remove this patch when fix the problem.
#
# * Worker Patch:
# ===============
#