PyTorch native quantization for training and inference
☆2,993Oct 7, 2026Updated this week
Alternatives and similar repositories for ao
Users that are interested in ao are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A PyTorch native platform for training generative AI models☆5,785Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,569Updated this week
- PyTorch native post-training library☆5,811Sep 9, 2026Updated 3 weeks ago
- Tile primitives for speedy kernels☆3,745Sep 12, 2026Updated 3 weeks ago
- FlashInfer: Kernel Library for LLM Serving☆6,556Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A pytorch quantization backend for optimum☆1,051Sep 29, 2026Updated last week
- Fast low-bit matmul kernels in Triton☆488Updated this week
- Efficient Triton Kernels for LLM Training☆6,647Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,153Sep 4, 2024Updated 2 years ago
- Development repository for the Triton language and compiler☆20,319Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆8,514Sep 7, 2026Updated last month
- Helpful tools and examples for working with flex-attention☆1,253Updated this week
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆959Updated this week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,259Aug 22, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Fast and memory-efficient exact attention☆25,099Updated this week
- Minimalistic large language model 3D-parallelism training☆2,831Sep 23, 2026Updated 2 weeks ago
- This repository contains the experimental PyTorch native float8 training UX☆226Aug 1, 2024Updated 2 years ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,557Sep 23, 2026Updated 2 weeks ago
- 🚀 Efficient implementations for emerging model architectures☆5,829Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,542Sep 23, 2026Updated 2 weeks ago
- Applied AI experiments and examples for PyTorch☆322Aug 22, 2025Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆959Feb 26, 2026Updated 7 months ago
- State-of-the-art LLM compression, built for production inference with vLLM☆3,855Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A Quirky Assortment of CuTe Kernels☆1,166Sep 17, 2026Updated 2 weeks ago
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆5,231Updated this week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆14,775Updated this week
- PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily wri…☆1,475Updated this week
- Ring attention implementation with flash attention☆1,062Sep 10, 2025Updated last year
- Distributed Compiler and Optimized Parallel Kernels☆1,557Sep 18, 2026Updated 2 weeks ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,649Jul 17, 2025Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,368Aug 28, 2025Updated last year
- depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.☆814Oct 13, 2025Updated 11 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,473Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆862Mar 6, 2025Updated last year
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,540Updated this week
- Cataloging released Triton kernels.☆314Sep 9, 2025Updated last year
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆398Jan 8, 2026Updated 9 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,835Updated this week
- Material for gpu-mode lectures☆6,788Sep 9, 2026Updated 3 weeks ago