Fast low-bit matmul kernels in Triton
☆493Oct 1, 2026Updated last month
Alternatives and similar repositories for gemlite
Users that are interested in gemlite are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆772Aug 6, 2025Updated last year
- Cataloging released Triton kernels.☆315Sep 9, 2025Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆964Feb 26, 2026Updated 8 months ago
- Applied AI experiments and examples for PyTorch☆321Aug 22, 2025Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,177Sep 4, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A Quirky Assortment of CuTe Kernels☆1,194Oct 30, 2026Updated 2 weeks ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆205Sep 2, 2026Updated 2 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆375Updated this week
- PyTorch native quantization for training and inference☆3,030Updated this week
- Framework to reduce autotune overhead to zero for well known deployments.☆101Sep 19, 2025Updated last year
- Tile primitives for speedy kernels☆3,803Sep 12, 2026Updated 2 months ago
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆985Updated this week
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆397Apr 13, 2025Updated last year
- ☆119Jul 28, 2026Updated 3 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Distributed Compiler and Optimized Parallel Kernels☆1,580Sep 18, 2026Updated last month
- ☆65Apr 26, 2025Updated last year
- extensible collectives library in triton☆98Mar 31, 2025Updated last year
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,618Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆351Jul 2, 2024Updated 2 years ago
- ☆40Dec 14, 2025Updated 11 months ago
- Collection of kernels written in Triton language☆201Jan 27, 2026Updated 9 months ago
- ☆271Jul 11, 2024Updated 2 years ago
- ☆20Sep 28, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Efficient Triton Kernels for LLM Training☆6,703Updated this week
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆119Oct 28, 2026Updated 2 weeks ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆607Aug 14, 2026Updated 3 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,937Updated this week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆130Jul 13, 2024Updated 2 years ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆82Aug 12, 2024Updated 2 years ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆282Jul 16, 2025Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆869Mar 6, 2025Updated last year
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆193Jan 28, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆499Nov 10, 2026Updated last week
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- Accelerating MoE with IO and Tile-aware Optimizations☆791Aug 29, 2026Updated 2 months ago
- ☆172Dec 27, 2024Updated last year
- ☆54May 19, 2025Updated last year
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Triton-based Symmetric Memory operators and examples☆114May 15, 2026Updated 6 months ago
Are these results useful?