NVIDIA / NVIDIA/TensorRT-LLM

Reasoning-related enhancements

Open
#3,965 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

feature request roadmap
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

  • [Ongoing] Support best-of-n and tree-search-based inference time compute methods.
  • [Ongoing] Support tool call within inference time compute method.
  • Provide infrastructure for prompt engineering.
  • [Ongoing] Provide infrastructure for token budgets.

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

No file, test, or entry point is named. Start by reviewing the repository's Python API and separating the four requested capabilities: best-of-n and tree-search inference, tool calls, prompt engineering, and token budgets. Done would require an agreed scope and implementation criteria for these broad infrastructure features.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
ai, backend, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.