tinygrad / open-gpu-kernel-modulesLinks
NVIDIA Linux open GPU with P2P support
☆1,234Updated 2 months ago
Alternatives and similar repositories for open-gpu-kernel-modules
Users that are interested in open-gpu-kernel-modules are comparing it to the libraries listed below
Sorting:
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆1,731Updated this week
- Tile primitives for speedy kernels☆2,629Updated 3 weeks ago
- ☆1,048Updated 3 months ago
- Distributed Training Over-The-Internet☆955Updated 3 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆868Updated last week
- Flash Attention in ~100 lines of CUDA (forward pass only)☆910Updated 8 months ago
- llama.cpp fork with additional SOTA quants and improved performance☆1,096Updated last week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆886Updated 11 months ago
- Serving multiple LoRA finetuned LLM as one☆1,083Updated last year
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆652Updated 4 months ago
- ☆450Updated 4 months ago
- Large-scale LLM inference engine☆1,530Updated this week
- TinyChatEngine: On-Device LLM Inference Library☆887Updated last year
- FlashAttention (Metal Port)☆523Updated 11 months ago
- ☆552Updated 10 months ago
- OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training☆528Updated 7 months ago
- PyTorch native quantization and sparsity for training and inference☆2,291Updated this week
- FlashInfer: Kernel Library for LLM Serving☆3,618Updated this week
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆4,290Updated last week
- Low-bit LLM inference on CPU/NPU with lookup table☆846Updated 2 months ago
- prime is a framework for efficient, globally distributed training of AI models over the internet.☆805Updated 3 months ago
- AMD Ryzen™ AI Software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen™ AI powered PCs.☆606Updated 2 weeks ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆663Updated 3 weeks ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,552Updated this week
- Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU. Seamlessly integrated with Torchao, Tra…☆607Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,861Updated this week
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆571Updated 2 weeks ago
- AI Tensor Engine for ROCm☆260Updated this week
- Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.☆2,351Updated last week
- DFloat11: Lossless LLM Compression for Efficient GPU Inference☆524Updated this week