modelscope / modelscope/DiffSynth-Studio

fp8 vs bf16

Open
#530 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.1k
Forks
1.3k
Avg merge
13h 12m
Merged PRs (30d)
45

Description

Image Why doesn't the use of float8 data precision result in a noticeable speed increase when compared to using bfloat16 data precision?

Contributor guide

No contributing guide indexed for this repository

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

The issue provides only an attached image and a question comparing fp8 with bfloat16, without naming files, tests, hardware, or a model configuration. Start by identifying the benchmark setup shown in the image and reproduce both precision modes under matching conditions. Done means explaining the missing speedup with evidence from a controlled comparison.

Written by the indexing model from the issue text.

Assessment

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.