NVIDIA / NVIDIA/TensorRT-LLM

1.0 Architecture

Open
#3,964 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

  • [Ongoing] Logits post-processor
  • [Ongoing] LoRA
  • Multi-modality model enablement
  • Sampling logics completeness
    • Beam search
    • Penalty
    • Stop words
  • Context Parallelism
  • Speculative decoding
    • [Ongoing] Eagle-3
    • Prompt look-up
    • Dynamic use of speculation based on load
  • Feature parity with TensorRT-based architecture: pls refer here to learn details as to achieve feature parity of the 1.0 architecture.
  • Post-training workflow integration

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 files, tests, or entry points are named. Start by locating the 1.0 architecture tracking material and the referenced TensorRT-based feature-parity details, then identify an independently scoped workstream from the list; done would require implementing and validating that workstream against the project's architecture goals.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.