Skills
.Work. You
Rest

vllm-mimo-v2-flash-optimization

Community

PR-backed MiMo-V2-Flash optimization in vLLM.

Software Engineering#optimization#runtime#inference#vllm#moe#mimo#mimo_v2_flash
AuthorBBuf
Version1.0.0
Installs0

System Documentation

What problem does it solve?

PR-backed optimization manual for MiMo-V2-Flash in vLLM. Use when Codex needs to audit, debug, extend, or document MiMo-V2-Flash inference-centric MoE runtime, MTP behavior, and the transition from older MiMo checkpoints in vLLM.

Core Features & Use Cases

  • PR-backed optimization guidance for MiMo-V2-Flash in vLLM, covering performance and correctness concerns.
  • MTP and MoE runtime focus on inference-centric behavior and the transition from legacy checkpoints.
  • Use Case: Engineers audit PR diffs, extend runtime models, and document MiMo-V2-Flash integration for reliable deployment.

Quick Start

Review the included PR history and apply MiMo-V2-Flash optimization steps to auditing, debugging, extending, and documenting the vLLM integration.

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: vllm-mimo-v2-flash-optimization
Download link: https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/archive/main.zip#vllm-mimo-v2-flash-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.