HazyResearch / ThunderKittensLinks
Tile primitives for speedy kernels
☆2,457Updated last week
Alternatives and similar repositories for ThunderKittens
Users that are interested in ThunderKittens are comparing it to the libraries listed below
Sorting:
- Puzzles for learning Triton☆1,695Updated 7 months ago
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆868Updated this week
- Flash Attention in ~100 lines of CUDA (forward pass only)☆845Updated 5 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,292Updated this week
- FlashInfer: Kernel Library for LLM Serving☆3,211Updated this week
- GPU programming related news and material links☆1,590Updated 5 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,491Updated this week
- Fast CUDA matrix multiplication from scratch☆746Updated last year
- PyTorch native quantization and sparsity for training and inference☆2,114Updated this week
- 🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton☆2,697Updated this week
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆554Updated this week
- A PyTorch native platform for training generative AI models☆3,933Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆822Updated 2 weeks ago
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,548Updated 2 weeks ago
- Distributed Compiler Based on Triton for Parallel Systems☆829Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆628Updated last month
- Pipeline Parallelism for PyTorch☆767Updated 10 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆845Updated 9 months ago
- What would you do with 1000 H100s...☆1,053Updated last year
- A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. …☆995Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,051Updated last year
- depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.☆689Updated 2 months ago
- An open-source efficient deep learning framework/compiler, written in python.☆703Updated this week
- Microsoft Automatic Mixed Precision Library☆609Updated 8 months ago
- Building blocks for foundation models.☆508Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆697Updated 3 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,803Updated this week
- Minimalistic large language model 3D-parallelism training☆1,926Updated last week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,426Updated 11 months ago
- A machine learning compiler for GPUs, CPUs, and ML accelerators☆3,280Updated this week