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

For nz unset in bf16&fp16 (#4495)

Browse Source 
<!--  Thanks for sending a pull request!

BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html

-->
### What this PR does / why we need it?
disable NZ for float weight case. This is only a quick fix for dev
branch.

For main branch, we'll consider more case to make it more common.


### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->

### How was this patch tested?
qwen2.5 32B
<img width="441" height="221" alt="image"
src="https://github.com/user-attachments/assets/7ae18ffd-1ce2-43d9-9960-be45250ad0da"
/>

---------

Signed-off-by: 刘哲续 <liuzhexu1@huawei.com>
Co-authored-by: 刘哲续 <liuzhexu1@huawei.com>
This commit is contained in:
henryxuxu0716
2025-11-28 17:32:25 +08:00
committed by GitHub
parent 96c362361e
commit 71acc8ddeb
10 changed files with 16 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/ops/common_fused_moe.py
View File

@@ -76,7 +76,7 @@ class AscendUnquantizedFusedMoEMethod(UnquantizedFusedMoEMethod):
w2_data = self._maybe_pad_weight(layer.w2_weight.data)
layer.w2_weight = torch.nn.Parameter(w2_data, requires_grad=False)
if not is_310p() and is_enable_nz():
if not is_310p() and is_enable_nz(layer.w13_weight.data.dtype):
layer.w13_weight.data = torch_npu.npu_format_cast(
layer.w13_weight.data, ACL_FORMAT_FRACTAL_NZ)
layer.w2_weight.data = torch_npu.npu_format_cast(