Skip to content

Conversation

HaiShaw
Copy link
Collaborator

@HaiShaw HaiShaw commented Nov 27, 2024

Motivation

Rename tuned config files from fused_moe_triton changes

Modifications

As it is.

This recovers most performance.
Still ~3.0-4.x% perf drop from v0.3.6.post2, which will be looked into further.

Checklist

  • [+] Format your code according to the Contributor Guide.
  • [+] Add unit tests as outlined in the Contributor Guide.
  • [+] Update documentation as needed, including docstrings or example tutorials.

@HaiShaw HaiShaw self-assigned this Nov 28, 2024
@HaiShaw HaiShaw enabled auto-merge (squash) November 28, 2024 04:16
@HaiShaw HaiShaw disabled auto-merge November 28, 2024 04:17
@HaiShaw HaiShaw merged commit cd51758 into sgl-project:main Nov 28, 2024
14 checks passed
@HaiShaw HaiShaw deleted the fused_moe_triton branch March 5, 2025 06:24
timethink pushed a commit to timethink/sglang that referenced this pull request Mar 9, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants