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

[Misc] Add extra checking to torchair_graph_config. (#1939)

Browse Source 
### What this PR does / why we need it?

cherry-pick #1675  to main
This PR adds validation checking to torchair_graph_config for better
reliability.

Co-authored-by: whx-sjtu <2952154980@qq.com>

### Does this PR introduce _any_ user-facing change?

No

### How was this patch tested?


- vLLM version: v0.10.0
- vLLM main:
2836dd73f1

Signed-off-by: 22dimensions <waitingwind@foxmail.com>
This commit is contained in:
22dimensions
2025-08-01 09:24:11 +08:00
committed by GitHub
parent 2284289880
commit 8cf97d8310
5 changed files with 100 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm_ascend/ops/fused_moe.py
View File

@@ -1232,7 +1232,8 @@ class AscendFusedMoE(FusedMoE):
self.torchair_graph_enabled = ascend_config.torchair_graph_config.enabled
self.enable_multistream_moe = \
ascend_config.torchair_graph_config.enable_multistream_moe
ascend_config.torchair_graph_config.enable_multistream_moe and \
self.torchair_graph_enabled
if self.scoring_func != "softmax" and not self.use_grouped_topk:
raise ValueError("Only softmax scoring function is supported for "