Skip to content

make trtllm attn backend's init_forward_metadat non blocking#13802

Merged
Fridge003 merged 1 commit intomainfrom
perf/remove_a_trtllm_attn_backend_sync_point
Nov 23, 2025
Merged

make trtllm attn backend's init_forward_metadat non blocking#13802
Fridge003 merged 1 commit intomainfrom
perf/remove_a_trtllm_attn_backend_sync_point

Conversation

@cicirori
Copy link
Collaborator

@cicirori cicirori commented Nov 23, 2025

Motivation

This is a minor performance fix. The original implementation caused a CPU-to-GPU copy, which in turn introduced a host–device synchronization point.

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

Loading
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants