Skip to content
View DefTruth's full-sized avatar
🎯
#pragma unroll
🎯
#pragma unroll

Organizations

@vipshop @PaddlePaddle @xlite-dev

Block or report DefTruth

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse

Pinned Loading

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

    🛠 A lite C++ toolkit: contains 100+ Awesome AI models, support MNN, NCNN, TNN, ONNXRuntime and TensorRT. 🎉🎉

    C++ 4k 737

  2. vllm-project/vllm vllm-project/vllm Public

    A high-throughput and memory-efficient inference and serving engine for LLMs

    Python 42.5k 6.4k

  3. xlite-dev/Awesome-LLM-Inference xlite-dev/Awesome-LLM-Inference Public

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

    3.7k 261

  4. xlite-dev/CUDA-Learn-Notes xlite-dev/CUDA-Learn-Notes Public

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

    Cuda 3k 309

  5. xlite-dev/ffpa-attn-mma xlite-dev/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 154 6

  6. xlite-dev/hgemm-mma xlite-dev/hgemm-mma Public

    ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.

    Cuda 62 2