Skip to content
View DefTruth's full-sized avatar
🎯
#pragma unroll
🎯
#pragma unroll
2.1k followers · 186 following

Achievements

Achievement: Pull Sharkx4Achievement: Starstruckx4Achievement: Pair Extraordinairex4Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx4Achievement: Starstruckx4Achievement: Pair Extraordinairex4Achievement: YOLOAchievement: Quickdraw

Organizations

@vipshop @PaddlePaddle @xlite-dev

Block or report DefTruth

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
DefTruth/README.md

Pinned Loading

  1. xlite-dev/LeetCUDA xlite-dev/LeetCUDA Public

    📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

    Cuda 11.4k 1.2k

  2. xlite-dev/lite.ai.toolkit xlite-dev/lite.ai.toolkit Public

    🛠A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion, etc.🎉

    C++ 4.4k 784

  3. PaddlePaddle/FastDeploy PaddlePaddle/FastDeploy Public

    High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

    Python 3.7k 756

  4. sgl-project/sglang sgl-project/sglang Public

    SGLang is a high-performance serving framework for large language models and multimodal models.

    Python 29.9k 6.8k

  5. vipshop/cache-dit vipshop/cache-dit Public

    A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.

    Python 1.2k 76

  6. xlite-dev/ffpa-attn xlite-dev/ffpa-attn Public

    🤖FFPA: Extends FlashAttention-2 via Split-D for large headdims, 1.5x~3×↑🎉 vs SDPA, up to 430T🎉 on H200.

    Python 311 22