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

[feature] add_rms_norm support bias (#5790)

Browse Source 
### What this PR does / why we need it?
This PR is to replace addRmsNorm and Add With addRmsNormBias. This way
can lead to a more effecient result.

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
Full Test Pass

- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef

Signed-off-by: Chen_HaoWen <chenhaowen12@huawei.com>
Co-authored-by: Chen_HaoWen <chenhaowen12@huawei.com>
This commit is contained in:
yjmyl
2026-01-23 21:09:54 +08:00
committed by GitHub
parent 6c73b88dd6
commit e90b14140b
24 changed files with 3537 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/e2e/singlecard/spec_decode/test_v1_spec_decode.py
View File

@@ -420,7 +420,7 @@ def test_llama_qwen_eagle_acceptance(
]
golden = BASELINES[method]
match = all(abs(a - b) < 0.06 for a, b in zip(acceptance_per_pos, golden))
match = all(abs(a - b) < 0.08 for a, b in zip(acceptance_per_pos, golden))
if not match:
print(f"acceptance_per_pos: {acceptance_per_pos}")
print(f"golden: {golden}")