pytorch / ao
PyTorch native quantization and sparsity for training and inference
☆1,944Updated this week
Alternatives and similar repositories for ao:
Users that are interested in ao are comparing it to the libraries listed below
- Tile primitives for speedy kernels☆2,227Updated this week
- A pytorch quantization backend for optimum☆913Updated last week
- FlashInfer: Kernel Library for LLM Serving☆2,611Updated this week
- A PyTorch native library for large model training☆3,562Updated this week
- Thunder gives you PyTorch models superpowers for training and inference. Unlock out-of-the-box optimizations for performance, memory and …☆1,320Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆2,346Updated this week
- Minimalistic large language model 3D-parallelism training☆1,771Updated this week
- Puzzles for learning Triton☆1,557Updated 4 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆528Updated last month
- nvidia-modelopt is a unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculat…☆851Updated last week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,193Updated this week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆978Updated last month
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,912Updated 2 weeks ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆778Updated last week
- 🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton☆2,216Updated this week
- Pipeline Parallelism for PyTorch☆761Updated 7 months ago
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆798Updated this week
- Helpful tools and examples for working with flex-attention☆707Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆931Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,998Updated 2 weeks ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,060Updated last month
- GPU programming related news and material links☆1,440Updated 3 months ago
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,167Updated 6 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,233Updated last month
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,377Updated 8 months ago
- On-device AI across mobile, embedded and edge for PyTorch☆2,694Updated this week
- Efficient Triton Kernels for LLM Training☆4,805Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆788Updated 7 months ago
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…☆1,564Updated last year
- Schedule-Free Optimization in PyTorch☆2,132Updated 2 weeks ago