Skills
.Work. You
Rest

vllm-kimi-optimization

Community

PR-backed optimization for Kimi models in vLLM.

Software Engineering#model-optimization#vllm#kimi#qa-validation#pr-diff-dossier#runtime-triage
AuthorBBuf
Version1.0.0
Installs0

System Documentation

What problem does it solve?

PR-backed optimization guidance for Kimi K2/K2.5/Linear/VL in vLLM to audit, debug, extend, or document Kimi-VL, Kimi-Linear, Kimi-K2.5, Kimi-Audio, parser aliases, and quantized MLA behavior.

Core Features & Use Cases

  • PR-diff dossiers for Kimi model families to capture diffs and rationale across Kimi-VL, Kimi-Linear, Kimi-K2.5, and Kimi-Audio in vLLM.
  • Cross-version runtime impact analysis, including TP/DP and MLA quantization considerations, with references to landed PRs and tests.
  • Use Case: When preparing a production deployment, pull the latest PR diffs from references/pr-history.md to validate compatibility and generate a production readiness dossier.

Quick Start

Load the latest vLLM Kimi optimization dossier and begin by reviewing the PR history in references/pr-history.md, then align local changes with the canonical diffs.

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