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

fix nz for quantization (#4943)

Browse Source 
quantization ops rely on NZ by force, we should remove the nz check for it.

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-12-12 14:54:41 +08:00
committed by GitHub
parent 5932abc446
commit 01a13a9b77
4 changed files with 11 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/quantization/w8a8.py
View File

@@ -347,7 +347,7 @@ class AscendW8A8FusedMoEMethod:
# converting ACL_FORMAT_FRACTAL_NZ.
# npu_quant_grouped_matmul_dequant in eager mode does not accept
# ACL_FORMAT_FRACTAL_NZ.
if not is_310p() and is_enable_nz():
if not is_310p():
layer.w13_weight.data = torch_npu.npu_format_cast(
layer.w13_weight.data, ACL_FORMAT_FRACTAL_NZ).contiguous()
layer.w2_weight.data = torch_npu.npu_format_cast(