Pinned Loading

1. lite.ai.toolkit lite.ai.toolkit Public

   🛠 A lite C++ toolkit that contains 100+ Awesome AI models (Stable-Diffusion, FaceFusion, YOLO series, Face/Object Detection, Seg, Matting, etc), support MNN, ORT and TensorRT. 🎉🎉

   C++ 4k 737

2. Awesome-LLM-Inference Awesome-LLM-Inference Public

   📖A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, FlashAttention, PagedAttention, MLA, Parallelism, Prefix Cache, Chunked Prefill, PD Disaggregate, etc. 🎉🎉

   Python 3.7k 264

3. CUDA-Learn-Notes CUDA-Learn-Notes Public

   📚Modern CUDA Learn Notes with PyTorch: 200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe API (Achieve 98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).

   Cuda 3.1k 328

4. statistic-learning-R-note statistic-learning-R-note Public

   📒《统计学习方法-李航: 笔记-从原理到实现》200-page PDF Notes, with detailed explanations of various math formulas, implementations of many algorithms using the R language. 🎉

   443 55

5. torchlm torchlm Public

   💎A high level python lib for face landmarks detection: training, eval, export, inference(Python/C++) and 100+ data augmentations.

   Python 255 24

6. ffpa-attn-mma ffpa-attn-mma Public

   📚FFPA(Split-D): Yet another Faster Flash Prefill Attention with O(1) GPU SRAM complexity for headdim > 256, ~2x↑🎉vs SDPA EA.

   Cuda 157 7