PyTorch native quantization for training and inference
Appears on
Quick read
Latest capture 2026-09-04 04:07
1 path
Agent instructions and tool configuration found in this repository.
Claude Code
97 observed captures since 2026-05-25. Observed captures are shown by default.
Stars from first capture +129
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Accessible large language models via k-bit quantization for PyTorch.
Go ahead and axolotl questions
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 post-training library
QLoRA: Efficient Finetuning of Quantized LLMs
A PyTorch native platform for training generative AI models
