NVIDIA / NVIDIA/TensorRT-LLM

[Feature]: Improve the performance of FP8 models

Open
#7,434 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

🚀 The feature, motivation and pitch

nvidia/Llama-3.1-8B-Instruct-FP8 is 2x slower than PT

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 reported performance difference for nvidia/Llama-3.1-8B-Instruct-FP8 versus the non-FP8 model, using the repository's documented examples and benchmarks. No files, tests, or entry points are named, and the issue does not define a target measurement or acceptance criteria; done would require demonstrating improved FP8 performance against the reported baseline.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.