xlite-dev
Develop ML/AI toolkits and ML/AI/CUDA Learning resources.
Pinned Loading
Repositories
Showing 10 of 23 repositories
- Awesome-LLM-Inference Public
📚A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, FlashAttention, PagedAttention, MLA, Parallelism etc.
- Awesome-Diffusion-Inference Public
📖A curated list of Awesome Diffusion Inference Papers with codes: Sampling, Caching, Multi-GPUs, etc. 🎉🎉
- lite.ai.toolkit Public
🛠 A lite C++ AI toolkit: 100+🎉 models (Stable-Diffusion, Face-Fusion, YOLO series, Det, Seg, Matting) with MNN, ORT and TRT.
- 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, implemented in R.🎉
- ffpa-attn-mma Public
📚FFPA(Split-D): Extend FlashAttention with Split-D for large headdim, O(1) GPU SRAM complexity, 1.8x~3x↑🎉 faster than SDPA EA.
- hgemm-tensorcores-mma Public
⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
- SageAttention Public Forked from thu-ml/SageAttention
Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.
