Skip to content

Commit

Permalink
use device param in load_model method (vllm-project#13037)
Browse files Browse the repository at this point in the history
  • Loading branch information
Zzhiter authored and kerthcet committed Feb 21, 2025
1 parent d20cde2 commit 3f5fe64
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion vllm/worker/model_runner.py
Original file line number Diff line number Diff line change
Expand Up @@ -1107,7 +1107,7 @@ def __init__(

def load_model(self) -> None:
logger.info("Starting to load model %s...", self.model_config.model)
with DeviceMemoryProfiler() as m:
with DeviceMemoryProfiler(self.device) as m:
self.model = get_model(vllm_config=self.vllm_config)

self.model_memory_usage = m.consumed_memory
Expand Down

0 comments on commit 3f5fe64

Please sign in to comment.