NVIDIA / NVIDIA/TensorRT-LLM

seq_slot_manager.py uses undefined name 'logger'

Open Beginner friendly
#18,776 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Disaggregated serving Pytorch
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

In tensorrt_llm/_torch/pyexecutor/seq_slot_manager.py (line 20), logger.info(...) is called but logger is never imported or defined in the module — grep -n logger in that file hits only line 20. The surrounding files in _torch/pyexecutor/ import it via from tensorrt_llm.logger import logger.

Trigger: PyTorch backend scheduling any request with is_disagg_generation_init_state (disaggregated serving context-phase requests) raises NameError: name 'logger' is not defined instead of skipping slot assignment.

Found via ruff F821 + manual verification (only genuine F821 of the sweep). Happy to send a one-line PR adding the import if accepted.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with tensorrt_llm/_torch/pyexecutor/seq_slot_manager.py around line 20 and compare logger imports in surrounding _torch/pyexecutor/ files. Run the reported ruff F821 check, then exercise the PyTorch backend scheduling path for a request with is_disagg_generation_init_state. Done means the NameError is gone and the request skips slot assignment as intended.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
backend
Issue type
Bug
Difficulty
1/5
Estimated time
Under an hour
Activity status
Active
Clarity
Clearly specified
Newbie friendliness
90/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.