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

[BugFix] Fix some issues caused by the ascending order of cudagraph_capture_sizes (#4338)

Browse Source 
### What this PR does / why we need it?
In [#26016](https://github.com/vllm-project/vllm/pull/26016), vllm
change the `cudagraph_capture_sizes` to be in ascending order. This PR
fixes related issues caused by this.
### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?


- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

---------

Signed-off-by: Angazenn <supperccell@163.com>
This commit is contained in:
Angazenn
2025-11-22 17:33:12 +08:00
committed by GitHub
parent fff258bce1
commit 9b3a484b46
3 changed files with 13 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/e2e/multicard/test_aclgraph_capture_replay.py
View File

@@ -109,7 +109,7 @@ def _run_worker_process(
llm = LLM(
model=model_path,
quantization="ascend" if "W8A8" in model_path else None,
# enable_expert_parallel=True if "DeepSeek" in model_path else False,
enable_expert_parallel=True if "DeepSeek" in model_path else False,
trust_remote_code=True,
)