Libraries-Openly-Fused / FusedKernelLibraryLinks
Implementation of a methodology that allows all sorts of user defined GPU kernel fusion, for non CUDA programmers.
☆28Updated last week
Alternatives and similar repositories for FusedKernelLibrary
Users that are interested in FusedKernelLibrary are comparing it to the libraries listed below
Sorting:
- ☆109Updated 6 months ago
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆90Updated 2 months ago
- ☆50Updated 6 months ago
- Efficient implementation of DeepSeek Ops (Blockwise FP8 GEMM, MoE, and MLA) for AMD Instinct MI300X☆71Updated 2 weeks ago
- ☆31Updated 4 months ago
- Quantized Attention on GPU☆44Updated last year
- Framework to reduce autotune overhead to zero for well known deployments.☆85Updated 2 months ago
- Evaluating Large Language Models for CUDA Code Generation ComputeEval is a framework designed to generate and evaluate CUDA code from Lar…☆74Updated last month
- TritonParse: A Compiler Tracer, Visualizer, and Reproducer for Triton Kernels☆171Updated last week
- How to ensure correctness and ship LLM generated kernels in PyTorch☆121Updated last week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆286Updated this week
- a size profiler for cuda binary☆52Updated last month
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 4 months ago
- A bunch of kernels that might make stuff slower 😉☆64Updated this week
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆134Updated last week
- Example of applying CUDA graphs to LLaMA-v2☆12Updated 2 years ago
- The evaluation framework for training-free sparse attention in LLMs☆103Updated last month
- ☆107Updated this week
- DeeperGEMM: crazy optimized version☆73Updated 6 months ago
- Parallel framework for training and fine-tuning deep neural networks☆68Updated 2 weeks ago
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆47Updated 3 months ago
- ☆130Updated 5 months ago
- A faster implementation of OpenCV-CUDA that uses OpenCV objects, and more!☆54Updated last week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆210Updated this week
- ☆22Updated 4 months ago
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆32Updated 11 months ago
- ☆121Updated 3 months ago
- extensible collectives library in triton☆91Updated 7 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆100Updated 4 months ago
- ☆71Updated 7 months ago