Skip to content

Remove redundant sampler check in TrajectoryCollectorEngine. #1825

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
copybara-service merged 1 commit into from
Aug 7, 2026
Merged

Remove redundant sampler check in TrajectoryCollectorEngine. #1825

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
40 changes: 17 additions & 23 deletions tunix/experimental/rollout/collector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,29 +71,23 @@ async def model_call(
if max_generation_steps is not None:
generation_kwargs["max_tokens"] = max_generation_steps

if self.sampler:
sampling_params = sampler_lib.SamplingParams(
max_tokens=generation_kwargs.get("max_tokens", 64),
temperature=generation_kwargs.get("temperature", 0.0),
top_p=generation_kwargs.get("top_p", None),
top_k=generation_kwargs.get("top_k", None),
seed=generation_kwargs.get("seed", None),
return_logprobs=generation_kwargs.get("return_logprobs", False),
)
sampling_req = sampler_lib.SamplingRequest(
request_id=self.traj_id,
prompt=chat_completions,
sampling_params=sampling_params,
)
res = await self.sampler.sample(sampling_req, **generation_kwargs)
text = res if isinstance(res, str) else getattr(res, "text", str(res))
tokens = getattr(res, "token_ids", np.array([], dtype=np.int32))
logprobs = getattr(res, "logprobs", None)
else:
raise RuntimeError(
"TrajectoryCollectorEngine requires a valid sampler instance to"
" execute model_call."
)
sampling_params = sampler_lib.SamplingParams(
max_tokens=generation_kwargs.get("max_tokens", 64),
temperature=generation_kwargs.get("temperature", 0.0),
top_p=generation_kwargs.get("top_p", None),
top_k=generation_kwargs.get("top_k", None),
seed=generation_kwargs.get("seed", None),
return_logprobs=generation_kwargs.get("return_logprobs", False),
)
sampling_req = sampler_lib.SamplingRequest(
request_id=self.traj_id,
prompt=chat_completions,
sampling_params=sampling_params,
)
res = await self.sampler.sample(sampling_req, **generation_kwargs)
text = res if isinstance(res, str) else getattr(res, "text", str(res))
tokens = getattr(res, "token_ids", np.array([], dtype=np.int32))
logprobs = getattr(res, "logprobs", None)

return base_rollout.RolloutOutput(
text=[text],
Expand Down
Loading