HazyResearch / ThunderKittensLinks
Tile primitives for speedy kernels
☆2,579Updated 2 weeks ago
Alternatives and similar repositories for ThunderKittens
Users that are interested in ThunderKittens are comparing it to the libraries listed below
Sorting:
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆1,688Updated this week
- Puzzles for learning Triton☆1,925Updated 9 months ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆906Updated 7 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,530Updated this week
- GPU programming related news and material links☆1,658Updated 7 months ago
- PyTorch native quantization and sparsity for training and inference☆2,251Updated this week
- FlashInfer: Kernel Library for LLM Serving☆3,571Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,645Updated last week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,673Updated last month
- Fast CUDA matrix multiplication from scratch☆798Updated last year
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆568Updated last week
- 🚀 Efficient implementations of state-of-the-art linear attention models☆3,045Updated this week
- A PyTorch native platform for training generative AI models☆4,272Updated this week
- PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily wri…☆1,388Updated last week
- Distributed Compiler based on Triton for Parallel Systems☆1,031Updated last week
- What would you do with 1000 H100s...☆1,087Updated last year
- depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.☆715Updated 4 months ago
- Minimalistic large language model 3D-parallelism training☆2,130Updated last month
- NanoGPT (124M) in 3 minutes☆3,037Updated last month
- Pipeline Parallelism for PyTorch☆774Updated last year
- Helpful tools and examples for working with flex-attention☆938Updated last week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆527Updated this week
- UNet diffusion model in pure CUDA☆615Updated last year
- Building blocks for foundation models.☆532Updated last year
- A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. …☆1,120Updated this week
- An open-source efficient deep learning framework/compiler, written in python.☆715Updated 3 weeks ago
- Muon is an optimizer for hidden layers in neural networks☆1,547Updated last month
- A throughput-oriented high-performance serving framework for LLMs☆872Updated last week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,207Updated last month
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆880Updated 11 months ago