pytorch / pytorch/TensorRT

📖 [Story] Support LLM models end-end inference

Open
#2,911 0 comments 0 reactions 1 assignee View on GitHub

@peri044 is already working on this.

Since Jun 13, 2024.

Story story: LLM & Generative AI
Dominant language
Python
Stars
3k
Forks
410
Avg merge
3d 18h
Merged PRs (30d)
78

Description

TL;DR

Configuration: llm_examples_main branch and transformers version == 4.41.2
Support LLM models. Here's two of them and more are being tested internally.

  1. GPT2
  2. Llama2
  3. Llama3

Goal(s)

End-End compilation of LLM models

Tasks

### Tasks
- [ ] https://github.com/pytorch/TensorRT/issues/2912
- [ ] https://github.com/pytorch/TensorRT/issues/2913
- [ ] https://github.com/pytorch/pytorch/issues/128548
- [ ] https://github.com/pytorch/pytorch/issues/128385
- [ ] https://github.com/pytorch/pytorch/issues/124502
- [ ] https://github.com/pytorch/TensorRT/issues/2916
- [ ] https://github.com/pytorch/TensorRT/issues/2922
- [ ] https://github.com/pytorch/pytorch/issues/129423
- [ ] https://github.com/pytorch/TensorRT/issues/2964

Additional context

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.