skills.rest
BBuf
BBufCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

vllm-kimi-optimization

Analyze Kimi optimization PR diffs in vLLM for runtime compatibility.

721|65|Updated Apr 1, 2026
Search Tags:#model-optimization#vllm#kimi#qa-validation#pr-diff-dossier#runtime-triage
One-click install
npx skills add https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS --skill vllm-kimi-optimization
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vllm-kimi-optimization
Source: https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/tree/main/skills/model-optimization/vllm/vllm-kimi-optimization
Command: npx skills add https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS --skill vllm-kimi-optimization

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

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.

Frequently Asked Questions about vllm-kimi-optimization

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I validate vLLM compatibility for Kimi K2.5 and Kimi-VL models?▼

You can analyze Kimi optimization PR diffs in vLLM to ensure compatibility across Kimi-VL, Kimi-Linear, Kimi-K2.5, and Kimi-Audio. It validates changes against mainline commits and documented production diff dossiers.

What is the best way to analyze tensor parallelism impact for Kimi models in vLLM?▼

Analyzing tensor parallelism impact involves reviewing landed PR diffs that capture runtime path changes. This PR-backed analysis covers tensor parallelism, data parallelism, and MLA quantization considerations for Kimi models.

Does vLLM support quantized MLA behavior for Kimi-Audio and Kimi-Linear?▼

Yes, vLLM supports quantized MLA behavior for Kimi-Audio and Kimi-Linear through landed optimization PRs. You can audit and debug this behavior by aligning local changes with the canonical production diff dossiers.

How do I generate a production readiness dossier for Kimi K2 deployments in vLLM?▼

To generate a production readiness dossier for Kimi K2 deployments in vLLM, pull the latest PR diffs from references/pr-history.md to validate compatibility. This dossier captures diffs and rationale across Kimi model families.

Why do Kimi model parser aliases fail after updating vLLM mainline commits?▼

Kimi model parser aliases may fail after updating vLLM mainline commits due to unaligned local changes. Validate changes against the current mainline commits and the production diff dossiers to resolve this.

Related Skills

Explore More Software Engineering Skills→
BBufBBuf
721

vllm-intern-s1-optimization

Audit and optimize Intern-S1 integration and multimodal processing in vLLM.

Community
Advanced
peteromalletpeteromallet
97

serving-llms-vllm

Deploy LLM inference with vLLM using OpenAI-compatible endpoints, quantization, and tensor parallelism.

Community
Intermediate
dawsonblockdawsonblock

serving-llms-vllm

Serve OpenAI-compatible LLM endpoints with vLLM and PagedAttention.

Community
Advanced
BBufBBuf
721

vllm-internvl35-optimization

Document PR-backed optimization workflows for InternVL3.5 in vLLM.

Community
Advanced