SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLM, VLM, and video generation models.

Dockerized vLLM serving for Kimi-Linear-48B-A3B (AWQ-4bit), from 128K to 1M context.

🧗‍♂️ harleyszhang 的个人博客

Interpretation code for analyzing LLMs compression effects for the paper "When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models"

AWQ Quantization of Microsoft/Phi-4-Reasoning

Production-grade vLLM serving with an OpenAI-compatible API, per-request LoRA routing, KEDA autoscaling on Prometheus metrics, Grafana/OTel observability, and a benchmark comparing AWQ vs GPTQ vs GGUF.

An OpenAI Compatible API which integrates LLM, Embedding and Reranker. 一个集成 LLM、Embedding 和 Reranker 的 OpenAI 兼容 API

Effortlessly quantize, benchmark, and publish Hugging Face models with cross-platform support for CPU/GPU. Reduce model size by 75% while maintaining performance.

This project takes the Flan-T5 LLM and applies QLoRA and AWQ quantization techniques

Artificial Personality is text2text AI chatbot that can use character cards

Quantize LLM using AWQ

This repository contains notebooks and resources related to the Software Development Group Project (SDGP) machine learning component. Specifically, it includes two notebooks used for creating a dataset and fine-tuning a Mistral-7B-v0.1-Instruct model.

programmable filter, as posix awq, with ruby syntaxe and embeddable function