tile-ai / tilelang
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
☆858Updated this week
Alternatives and similar repositories for tilelang:
Users that are interested in tilelang are comparing it to the libraries listed below
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆778Updated this week
- Puzzles for learning Triton, play it with minimal environment configuration!☆267Updated 3 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆566Updated last month
- FlagGems is an operator library for large language models implemented in Triton Language.☆463Updated this week
- flash attention tutorial written in python, triton, cuda, cutlass☆308Updated 2 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆326Updated this week
- A Easy-to-understand TensorOp Matmul Tutorial☆332Updated 6 months ago
- Fast CUDA matrix multiplication from scratch☆666Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆617Updated 3 weeks ago
- FlashInfer: Kernel Library for LLM Serving☆2,483Updated this week
- Flash Attention in ~100 lines of CUDA (forward pass only)☆747Updated 3 months ago
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆374Updated 6 months ago
- depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.☆614Updated 3 months ago
- A throughput-oriented high-performance serving framework for LLMs☆782Updated 6 months ago
- Zero Bubble Pipeline Parallelism☆375Updated 3 weeks ago
- Materials for learning SGLang☆355Updated last week
- A PyTorch Native LLM Training Framework☆763Updated 3 months ago
- Step-by-step optimization of CUDA SGEMM☆294Updated 3 years ago
- A collection of memory efficient attention operators implemented in the Triton language.☆253Updated 9 months ago
- Fastest kernels written from scratch☆202Updated 3 weeks ago
- Applied AI experiments and examples for PyTorch☆250Updated last week
- Ring attention implementation with flash attention☆717Updated last month
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆524Updated last month
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆811Updated last week
- Cataloging released Triton kernels.☆212Updated 2 months ago
- Tile primitives for speedy kernels☆2,184Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆242Updated 5 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆458Updated last week
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆423Updated 6 months ago
- Microsoft Automatic Mixed Precision Library☆585Updated 6 months ago