vllm-project/vllm

[Feature]: Fused Kernel for GPT-OSS Router

Closed

#28,986 opened on Nov 19, 2025

View on GitHubContributor guide
 (10 comments) (0 reactions) (0 assignees)Python (16,816 forks)batch import
feature requestgood first issuehelp wantedstale

Repository metrics

Stars
 (80,034 stars)
PR merge metrics
 (Avg merge 3d 17h) (993 merged PRs in 30d)

Description

🚀 The feature, motivation and pitch

  • Right now, we spend ~3.5% of the layer in the expert selection
  • The operation is unfused

Write a fused kernel like we have for deepseek grouped_topk

Alternatives

  • torch compile
  • triton
  • cuda

Additional context

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

Contributor guide

Research direction
Study the existing grouped topk fused kernel in deepseek and adapt it for the GPT OSS router. Profile the current expert selection to understand the bottleneck, then implement a fused kernel using Triton or CUDA.
Tech stack
pythoncpp
Domain
machine learningaiperformancebackend
Issue type
Performance
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
pythoncpp
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
25