vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-10 23:34:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update install doc and fix local_chat bug

Browse source
This commit is contained in:
dongjw 2025-04-03 12:42:41 +08:00
parent ab0b0f4ea1
commit 1b7672937b
4 changed files with 14 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ktransformers/operators/attention.py
View file

@ -422,6 +422,7 @@ class KDeepseekV2Attention(BaseInjectedModule, DeepseekV2Attention):
if q_len == 1:
self.mla_wrapper.plan(None,None,None,
position_ids.squeeze(1)+1,
None,
self.num_heads,
self.kv_lora_rank,
self.qk_rope_head_dim,