pytorch / ao
PyTorch native quantization and sparsity for training and inference
☆1,889Updated this week
Alternatives and similar repositories for ao:
Users that are interested in ao are comparing it to the libraries listed below
- A PyTorch native library for large model training☆3,420Updated this week
- Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors a…☆1,298Updated this week
- Minimalistic large language model 3D-parallelism training☆1,657Updated this week
- Tile primitives for speedy kernels☆2,130Updated this week
- FlashInfer: Kernel Library for LLM Serving☆2,322Updated this week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆921Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆2,249Updated this week
- A pytorch quantization backend for optimum☆892Updated this week
- Puzzles for learning Triton☆1,466Updated 3 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆763Updated 2 weeks ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆519Updated 2 weeks ago
- A unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, speculative decoding, et…☆771Updated last week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,819Updated last week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,065Updated this week
- Pipeline Parallelism for PyTorch☆754Updated 6 months ago
- 🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton☆2,069Updated this week
- Helpful tools and examples for working with flex-attention☆676Updated this week
- Schedule-Free Optimization in PyTorch☆2,108Updated last week
- PyTorch native post-training library☆4,972Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,001Updated this week
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆2,802Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆750Updated 5 months ago
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,519Updated 4 months ago
- NanoGPT (124M) in 3 minutes☆2,360Updated this week
- GPU programming related news and material links☆1,406Updated 2 months ago
- UNet diffusion model in pure CUDA☆598Updated 8 months ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆721Updated 2 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,207Updated this week
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,162Updated 5 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,356Updated 7 months ago