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

Jump to bottom

[Bugfix] Fix KV head calculation for MPT models when using GQA #5142

Merged
merged 1 commit into from
Jun 17, 2024
Merged

[Bugfix] Fix KV head calculation for MPT models when using GQA #5142

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
6 changes: 5 additions & 1 deletion vllm/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -292,7 +292,11 @@ def get_total_num_kv_heads(self) -> int:
return 1

# For DBRX and MPT
if self.hf_config.model_type in ["dbrx", "mpt"]:
if self.hf_config.model_type == "mpt":
if "kv_n_heads" in self.hf_config.attn_config:
return self.hf_config.attn_config["kv_n_heads"]
return self.hf_config.num_attention_heads
if self.hf_config.model_type == "dbrx":
return getattr(self.hf_config.attn_config, "kv_n_heads",
self.hf_config.num_attention_heads)

Expand Down
Loading