xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-04 12:46:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix mla prefill context performance (#13897)

Browse Source 
Signed-off-by: ZhongYingMatrix <zhongyingmatrix@gmail.com>
This commit is contained in:
Ying Zhong 2025-03-07 01:35:49 +08:00 committed by GitHub
parent e642ec962c
commit 9f1710f1ac
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/attention/backends/mla/common.py
View File

@ -1308,7 +1308,7 @@ class MLACommonImpl(MLAAttentionImpl[T], Generic[T]):
)
kv_c_normed = workspace[:toks]\
[..., :self.kv_lora_rank].unsqueeze(1)
[..., :self.kv_lora_rank]
k_pe = workspace[:toks]\
[..., self.kv_lora_rank:].unsqueeze(1)

2
vllm/v1/attention/backends/mla/common.py
View File

@ -874,7 +874,7 @@ class MLACommonImpl(MLAAttentionImpl[M], Generic[M]):
)
kv_c_normed = workspace[:toks]\
[..., :self.kv_lora_rank].unsqueeze(1)
[..., :self.kv_lora_rank]
k_pe = workspace[:toks]\
[..., self.kv_lora_rank:].unsqueeze(1)