Skip to main content

vLLM

Skills/MLOps
MLOps

vLLM

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Enabled by defaultBuilt In
CLI install commandaegis skills install vllm
Install guide
Overview

Bundled with the packaged Aegis CLI as a built-in procedural skill.

Already ships inside the packaged Aegis bundle. Use `aegis skills install vllm` only when you want an explicit local materialization record.

Continue browsing

Also in MLOps

Model, inference, evaluation, and retrieval workflows kept explicit, reproducible, and operator-owned.

View full section
AudioCraft

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.

audiocraftView skill
Axolotl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

axolotlView skill
CLIP

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

clipView skill