Hqq Quantization
Skill Verified ActiveHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.
To enable users to quantize large language models efficiently and without calibration data, significantly reducing model size and memory footprint for faster inference and deployment.
Features
- Calibration-free quantization for LLMs
- Supports 8/4/3/2/1-bit precision
- Multiple optimized inference backends (Marlin, TorchAO, etc.)
- Seamless integration with HuggingFace Transformers and vLLM
- Compatibility with PEFT/LoRA for fine-tuning quantized models
Use Cases
- Quantizing LLMs to 4-bit precision without needing calibration datasets
- Performing fast quantization workflows for model compression
- Deploying quantized LLMs with vLLM or HuggingFace Transformers
- Fine-tuning quantized LLMs using PEFT and LoRA
Non-Goals
- Providing calibration-based quantization methods like AWQ or GPTQ
- Performing model training from scratch
- Serving models directly (relies on integration with frameworks like vLLM)
Installation
First, add the marketplace
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs/plugin install AI-Research-SKILLs@ai-research-skillsQuality Score
VerifiedTrust Signals
Similar Extensions
Arize Prompt Optimization
100Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.
Unsloth
100Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Prompt Optimization
100Applies prompt repetition to improve accuracy for non-reasoning LLMs
Vector Index Tuning
99Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
VLLM High Performance LLM Serving
97Serves 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.
Quantizing Models Bitsandbytes
97Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.