NVIDIA / NVIDIA/TensorRT-LLM

TRTLLM worker failed when prompt length is large than max_tokens

Open
#3,576 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug Decoding/Sampling Inference runtime Scaffolding
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

TRTLLM worker failed when prompt length is large than max_tokens. We need to handle this issue on scaffolding level.

Image

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

The issue identifies the TRTLLM worker and asks for handling at the scaffolding level, but names no files, tests, or expected behavior. Start by locating the worker's prompt and max_tokens handling, reproduce the failure with a prompt longer than max_tokens, and clarify the intended successful behavior before defining completion criteria.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, backend
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.