sglang-qwen-vlm-omni-asr-optimization
CommunityPR-diff-driven Qwen VLM/Omni/ASR optimization.
System Documentation
What problem does it solve?
PR-diff-backed optimization manual for Qwen2.5-VL, Qwen3-VL, Qwen3-VL-MoE, Qwen3-Omni, Qwen3-ASR, and Qwen3-5 multimodal paths in SGLang. Use when Codex needs to audit, debug, extend, or document multimodal processors, ViT DP/PP/chunk/cache, mRoPE, DeepStack, EAGLE3, LoRA, audio encoder, streaming ASR, encoder disaggregation, AMD/NPU/CPU support, or Qwen VLM cookbook deployment recipes.
Core Features & Use Cases
- PR-diff-driven guidance: channels best-practice paths for Qwen multimodal optimization, including VLM, Omni, ASR, and DP/PP/encoder considerations.
- Reference-driven workflow: integrates PR history and playbook references to reproduce and validate changes on real deployments.
- Comprehensive scope: covers Qwen2.5-VL, Qwen3-VL, Qwen3-VL-MoE, Qwen3-Omni, Qwen3-ASR, and related cross-family recipes.
Quick Start
Review the PR history in references/pr-history.md, then consult references/playbook.md and begin following the Qwen optimization workflow.
Dependency Matrix
Required Modules
None requiredComponents
💻 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-qwen-vlm-omni-asr-optimization Download link: https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/archive/main.zip#sglang-qwen-vlm-omni-asr-optimization Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.