NVIDIA / NVIDIA/TensorRT-LLM

[AutoDeploy]: test and improve the performance of quantized models

Open
#7,046 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

🚀 The feature, motivation and pitch

Example: nvidia/Llama-3.1-70B-Instruct-FP8 performs much worse compared to meta-llama/Meta-Llama-3.1-70B-Instruct (world=8)

Alternatives

No response

Additional context

No response

Before submitting a new issue...
  • Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

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 by reproducing the performance comparison between nvidia/Llama-3.1-70B-Instruct-FP8 and meta-llama/Meta-Llama-3.1 using world=8. Identify the relevant quantized-model benchmark or AutoDeploy entry point, then define completion as documented testing and a measurable performance improvement; the issue does not name files or tests.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning, performance
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.