EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Fusion] [Graph]Add Matmul Allreduce Rmsnorm fusion Pass (#5034)

Browse Source 
This PR add `MatmulAllreduceRmsnorm` operator and introduces a graph
fusion pass for `matmul_allreduce_rmsnorm` operations. The
implementation includes a new configuration flag, a pattern matching
pass using `torch._inductor.pattern_matcher`.

Co-authored-by: Trunrain [270250579@qq.com](mailto:270250579@qq.com)

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: wxsIcey <1790571317@qq.com>
Signed-off-by: tongrunze <t00574058@china.huawei.com>
This commit is contained in:
Icey
2026-01-19 09:28:07 +08:00
committed by GitHub
parent 9cad1a8349
commit c929bd1e8d
8 changed files with 251 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm_ascend/patch/worker/__init__.py
View File

@@ -22,6 +22,7 @@ if HAS_TRITON:
# isort: off
import vllm_ascend.patch.platform.patch_sched_yield # noqa
import vllm_ascend.patch.worker.patch_unquantized_gemm # noqa
import vllm_ascend.patch.worker.patch_bert # noqa
import vllm_ascend.patch.worker.patch_distributed # noqa
import vllm_ascend.patch.worker.patch_deepseek # noqa