Skip to content

[https://nvbugs/6428092][fix] Forward use_host_stop_criteria alongside host and py_result_diffs in the PP… #16133

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
trtllm-agent wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[https://nvbugs/6428092][fix] Forward use_host_stop_criteria alongside host and py_result_diffs in the PP… #16133

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7a40577
[nvbugs/6428092][fix] Propagate use_host_stop_criteria across PP ranks
trtllm-agent Jul 8, 2026
3e70f27
[nvbugs/6428092][chore] Remove stale waiver after fix
trtllm-agent Jul 24, 2026
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
15 changes: 10 additions & 5 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 @@ -3335,10 +3335,14 @@ def _ring_broadcast_sample_state(
if not self.dist.is_last_pp_rank:
# Receive tokens from previous pp rank (w.r.t model forward direction)
with nvtx_range("recv_sample_state"):
sample_state.host, py_result_diffs = self.dist.recv_object(
src=self.dist.prev_pp_rank,
tag=tag,
)
sample_state.host, py_result_diffs, use_host_stop_criteria = \
self.dist.recv_object(src=self.dist.prev_pp_rank, tag=tag)

# Propagate use_host_stop_criteria: the last rank's fast host-stop
# path leaves host.finish_reasons=None, so non-last ranks must
# know to skip the finish_reasons indexing in update_requests.
if hasattr(sample_state, "use_host_stop_criteria"):

@achartier achartier Jul 10, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No need for that check

@brnguyen2 brnguyen2 Aug 11, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

hasattr(sample_state, "use_host_stop_criteria") is always False: no sampler state class in the tree defines that attribute, and nothing assigns it. This branch never executes, and the matching getattr(..., False) on line 3115 always sends False. Before revising, confirm the field name against the real sampler state and re-verify the failing test actually reproduces and then passes.

sample_state.use_host_stop_criteria = use_host_stop_criteria

for request, py_result_diff in zip(requests, py_result_diffs):
request.py_result.apply_diff(py_result_diff)
Expand All @@ -3356,7 +3360,8 @@ def _ring_broadcast_sample_state(
self.wait_on_pp_send_handles(self.send_handles, microbatch_id)
with nvtx_range("send_sample_state"):
self.send_handles[microbatch_id] = self.dist.isend_object(
(sample_state.host, py_result_diffs),
(sample_state.host, py_result_diffs,
getattr(sample_state, "use_host_stop_criteria", False)),

@achartier achartier Jul 10, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No need for that check

dest=self.dist.next_pp_rank,
tag=tag,
)
Expand Down
1 change: 0 additions & 1 deletion tests/integration/test_lists/waives.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -399,7 +399,6 @@ unittest/executor/test_rpc_proxy.py SKIP (https://nvbugs/5605741)
unittest/executor/test_rpc_worker.py SKIP (https://nvbugs/5605741)
unittest/llmapi/test_additional_model_outputs.py -m "gpu2" SKIP (https://nvbugs/6428091)
unittest/llmapi/test_llm.py::test_generate_with_detokenization_stop_words_streaming[/scratch.trt_llm_data/llm-models/gemma/gemma-3-1b-it] SKIP (https://nvbugs/6566772)
unittest/llmapi/test_llm_multi_gpu_pytorch.py -m "gpu2" SKIP (https://nvbugs/6428092)
unittest/llmapi/test_llm_multi_gpu_pytorch.py::test_llm_get_stats_pp2[False-False-True] SKIP (https://nvbugs/6432826)
unittest/llmapi/test_llm_pytorch.py::test_gqa_nemo_lora[None] SKIP (https://nvbugs/6162504)
unittest/llmapi/test_llm_pytorch.py::test_gqa_nemo_lora[cuda_graph_config0] SKIP (https://nvbugs/6162504)
Expand Down
Loading