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

[v0.11.0][Fix] Fixes attribute error in MLA implementation (#3617)

Browse Source 
### What this PR does / why we need it?
Corrects the attribute access for retrieving the device from `q_a_proj`
to `q_proj`. This prevents an `AttributeError` as `q_a_proj` does not
exist on the class instance.

### Does this PR introduce _any_ user-facing change?
None.

### How was this patch tested?
Need MLAPO tests.

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
This commit is contained in:
Yizhou
2025-10-22 15:49:18 +08:00
committed by GitHub
parent a0c3b8dd2d
commit 984efdc0d0
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/mla_v1.py
View File

@@ -737,7 +737,7 @@ class AscendMLAImpl(MLAAttentionImpl):
self.qb_qt_bias = qb_qt_bias.reshape(
self.num_heads * (self.qk_nope_head_dim + self.qk_rope_head_dim))
device = self.q_a_proj.weight.device
device = self.q_proj.weight.device
self.gamma1 = self.q_a_layernorm.weight.data
self.beta1 = self.q_a_layernorm.bias.data
self.gamma2 = self.kv_a_layernorm.weight.data