Skip to content

fix qwen3.5 mtp #1385

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
hiworldwzj merged 1 commit into from
Jul 9, 2026
Merged

fix qwen3.5 mtp #1385

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion lightllm/common/kv_cache_mem_manager/qwen3next_mem_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,8 @@ def __init__(

def get_att_input_params(self, layer_index: int) -> Tuple[Any, Any]:
if layer_index >= self.linear_config.all_layer_num:
layer_index -= self.linear_layer_num
# MTP draft full-attn layers are packed after the main model layers.
layer_index -= self.linear_config.linear_layer_num
else:
layer_index = layer_index // self.linear_config.full_attention_interval
return super().get_att_input_params(layer_index)
Expand Down
Loading