sgl-project/sglang

[Feature] Simplify `tree_speculative_sampling_target_only`

Open

#12,562 opened on Nov 3, 2025

View on GitHub
 (2 comments) (0 reactions) (0 assignees)Python (28,442 stars) (6,216 forks)auto 404
good first issue

Description

Checklist

Motivation

Some TODOs for newcomers to SGLang

  • Remove passing argument draft_probs
  • Add a more efficient kernel (torch/triton/cuda) for topk=1 special case.

Related resources

No response

Contributor guide

Tech stack
pythonpytorch
Domain
backendperformance
Issue type
feature
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.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
PythonPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50
Research direction
Locate the function tree speculative sampling target only in the codebase, remove the draft probs parameter from its signature and all calls, then implement an efficient custom kernel (using torch, triton, or CUDA) for the topk=1 special case to improve performance.