sglang-qwen36-optimization

Community

PR-backed optimization for Qwen3.6 in SGLang.

AuthorBBuf
Version1.0.0
Installs0

System Documentation

What problem does it solve?

PR-backed optimization guidance for Qwen3.6 deployment, auditing, and cookbook parity within SGLang, enabling reliable cross-checks between mainline and PRs.

Core Features & Use Cases

  • PR-driven optimization strategy for Qwen3.6 deployment variants (35B-A3B MoE and 27B dense)
  • Guidance on hybrid Gated Delta Networks, multimodal inputs, thinking preservation, Qwen3 reasoning parser, Qwen3-Coder tool parser, MTP, and Mamba scheduler
  • Reference to diff-driven PR history and playbooks for validation and reproducibility

Quick Start

Review the PR history in references/pr-history.md and adapt the Qwen3.6 deployment guidelines to your environment.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: sglang-qwen36-optimization
Download link: https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/archive/main.zip#sglang-qwen36-optimization

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.