SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
Appears on
Quick read
Latest capture 2026-09-06 10:54
1 path
Agent instructions and tool configuration found in this repository.
GitHub Copilot
1 observed capture since 2026-09-06. Observed captures are shown by default.
Stars from first capture 0
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
PyTorch native quantization for training and inference
Accessible large language models via k-bit quantization for PyTorch.
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
