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

[bugfix] Fix MHA model runtime error in aclgraph mode (#5397)

Browse Source 
### What this PR does / why we need it?
Currently, MHA models (eg: minicpm-2b, Baichuan-7b) will encounter
errors when running in piecewise graph mode, with error messages similar
to:
```
(E89999):  When layout is TND and PA not enabled, keyT(8) and valueT(8) must be equal to the last element of actualSeqenceLengthKV(5)[FUNC:CheckInputShapeWhenLayoutIsTND][FILE:prompt_flash_attention_tiling.cpp][LINE:3618]
```
The error occurs because the qkv in the Prefill stage is also padded,
causing the shape to be inconsistent with actual_seq_lengths.
Add unpadding logic for kv.

- vLLM version: release/v0.13.0
- vLLM main:
254f6b9867

Signed-off-by: Wang Kunpeng <1289706727@qq.com>
This commit is contained in:
Wang Kunpeng
2025-12-26 21:37:28 +08:00
committed by GitHub
parent 7685d0c239
commit bc5b7a5fb5
3 changed files with 16 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.github/workflows/_e2e_test.yaml vendored
View File

@@ -115,8 +115,7 @@ jobs:
pytest -sv --durations=0 tests/e2e/singlecard/test_sampler.py
pytest -sv --durations=0 tests/e2e/singlecard/test_vlm.py
pytest -sv --durations=0 tests/e2e/singlecard/test_xlite.py
# TODO: revert me when minicpm is fixed
# pytest -sv --durations=0 tests/e2e/singlecard/test_models.py
pytest -sv --durations=0 tests/e2e/singlecard/test_models.py
pytest -sv --durations=0 tests/e2e/singlecard/pooling/
pytest -sv --durations=0 tests/e2e/singlecard/compile/test_norm_quant_fusion.py
pytest -sv --durations=0 tests/e2e/singlecard/test_multistream_overlap_shared_expert.py