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

[Bugfix] Fix masked_fill_ function typo (#769)

Browse Source 
### What this PR does / why we need it?
Fix function name typo, make `mask_fill_` to `masked_fill_`

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

### How was this patch tested?
CI passed

Signed-off-by: ApsarasX <apsarax@outlook.com>
This commit is contained in:
ApsarasX
2025-05-06 21:54:52 +08:00
committed by GitHub
parent afe1767c17
commit d6e9417652
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/attention/attention.py
View File

@@ -135,7 +135,7 @@ class AttentionMaskBuilder:
context_len:] = self.splitfuse_mask_value
right_tensor = attn_mask[current_row:current_row + q_len,
context_len:seq_len]
right_tensor.mask_fill_(
right_tensor.masked_fill_(
right_tensor.tril() == self.splitfuse_mask_value, 0)
current_row += q_len