Skip to content

[None][chore] Add NVTX ranges to per-iteration ADP sync points in PyExecutor #16422

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

Open
lancelly wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −0
Open

[None][chore] Add NVTX ranges to per-iteration ADP sync points in PyExecutor #16422

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
2 changes: 2 additions & 0 deletions tensorrt_llm/_torch/pyexecutor/py_executor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3247,6 +3247,7 @@ def _handle_dynamic_draft_len(self,
if spec_config is not None and spec_config.is_linear_tree else
self.model_engine.max_total_draft_tokens)

@nvtx_range("_can_queue")
def _can_queue(self, scheduled_batch):

# can_queue_this_rank is for case that the batch is not empty on this rank, but empty on other ranks
Expand Down Expand Up @@ -3851,6 +3852,7 @@ def _check_benchmark_disagg_gate(self, scheduled_batch: ScheduledRequests,
return can_forward, True
return can_forward, False

@nvtx_range("_handle_disagg_cache_errors_synced")
def _handle_disagg_cache_errors_synced(self):
"""Rank-safe disagg cache error and poison handler.

Expand Down
Loading