Skip to content
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

[Bugfix] Fix num_heads value for simple connector when tp enabled #12074

Merged
merged 1 commit into from
Jan 20, 2025
Merged

[Bugfix] Fix num_heads value for simple connector when tp enabled #12074

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 vllm/distributed/kv_transfer/kv_connector/simple_connector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@ def __init__(
):

self.config = config.kv_transfer_config
self.tp_size = config.parallel_config.tensor_parallel_size

if self.config.kv_connector == "PyNcclConnector":
from vllm.distributed.kv_transfer.kv_pipe.pynccl_pipe import (
Expand Down Expand Up @@ -161,7 +162,7 @@ def send_kv_caches_and_hidden_states(
end_layer = model_executable.model.end_layer

model_config = model_executable.model.config
num_heads = model_config.num_key_value_heads
num_heads = int(model_config.num_key_value_heads / self.tp_size)
hidden_size = model_config.hidden_size
num_attention_heads = model_config.num_attention_heads
head_size = int(hidden_size / num_attention_heads)
Expand Down
Loading