Optimization and Inference Serving

Optimization and serving guidance for Flash Attention, quantization formats and methods, vLLM, TensorRT-LLM, llama.cpp, and SGLang.

Parent repository GitHub

Type: skill categories / Claude plugins
Repository: Orchestra-Research/AI-Research-SKILLs
Readiness: Usable for guided research workflows, but framework guidance, autonomous claims, and demo results require project-specific validation
Keywords: 7

Location

Repository path

10-optimization/; 12-inference-serving/

Invocation

/plugin install optimization@ai-research-skills or /plugin install inference-serving@ai-research-skills

Setup

Installation / activation

Model compression, quantization, latency, throughput, or serving tasks.

Keywords

optimizationinferencequantizationvLLMTensorRT-LLMllama.cppSGLang

Repository context

Orchestra-Research/AI-Research-SKILLs

MIT-licensed, cross-agent library of 98 stated SKILL.md research and engineering playbooks in 23 categories; for Claude Code it installs as individual or category skills and adds an autoresearch layer that routes literature, ideation, experimentation, analysis, artifact, and paper-writing work across domain skills.

AI researchMachine learning engineeringLarge language modelsModel trainingModel evaluationMechanistic interpretabilityInference and servingMLOps and infrastructureRetrieval-augmented generationMultimodal AIAI safety and alignmentScientific communication

Open full repository research