pytorch / aoLinks
PyTorch native quantization and sparsity for training and inference
☆2,168Updated this week
Alternatives and similar repositories for ao
Users that are interested in ao are comparing it to the libraries listed below
Sorting:
- A pytorch quantization backend for optimum☆962Updated last week
- Thunder gives you PyTorch models superpowers for training and inference. Unlock out-of-the-box optimizations for performance, memory and …☆1,372Updated last week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,529Updated last week
- A PyTorch native platform for training generative AI models☆4,032Updated this week
- Tile primitives for speedy kernels☆2,501Updated this week
- Puzzles for learning Triton☆1,747Updated 7 months ago
- A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. …☆1,028Updated last week
- FlashInfer: Kernel Library for LLM Serving☆3,306Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,616Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,127Updated last month
- Minimalistic large language model 3D-parallelism training☆2,012Updated this week
- Pipeline Parallelism for PyTorch☆769Updated 10 months ago
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,566Updated last month
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆561Updated 3 weeks ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆842Updated last week
- GPU programming related news and material links☆1,610Updated 6 months ago
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…☆2,449Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,438Updated last year
- Helpful tools and examples for working with flex-attention☆865Updated 2 weeks ago
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆1,540Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,053Updated last year
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆2,967Updated last week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,391Updated this week
- Flash Attention in ~100 lines of CUDA (forward pass only)☆859Updated 6 months ago
- depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.☆698Updated 2 months ago
- 🚀 Efficient implementations of state-of-the-art linear attention models☆2,876Updated this week
- Schedule-Free Optimization in PyTorch☆2,189Updated last month
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆852Updated 10 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,202Updated 2 months ago
- A throughput-oriented high-performance serving framework for LLMs☆835Updated last month