Skip to content

Disable enforcing eager mode for mllama and deepseek_v3 on hpu #713

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
merged 1 commit into from
Jan 21, 2025
Merged

Disable enforcing eager mode for mllama and deepseek_v3 on hpu #713

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/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -608,8 +608,9 @@ def _verify_cuda_graph(self) -> None:
self.max_model_len)

MODEL_NOT_SUPPORT_CUDA_GRAPH = ['deepseek_v3', 'mllama']
from vllm.platforms import current_platform
if (self.hf_config.model_type in MODEL_NOT_SUPPORT_CUDA_GRAPH
and not self.enforce_eager):
and not self.enforce_eager and not current_platform.is_hpu()):
logger.warning(
"CUDA graph is not supported for %s yet, fallback to the eager "
"mode.", self.hf_config.model_type)
Expand Down
Loading