Skip to content
@madsys-dev

MadSys Research Group

Popular repositories Loading

  1. deepseekv2-profile deepseekv2-profile Public

    Jupyter Notebook 156 19

  2. async-ucx async-ucx Public

    Asynchronous Rust bindings for UCX

    Rust 81 20

  3. sosp-paper19-ae sosp-paper19-ae Public

    The Artifact Evaluation Version of SOSP Paper #19

    C++ 55 12

  4. smart smart Public

    Scaling Up Memory Disaggregated Applications with SMART (ASPLOS 24): Predecessor of Mooncake TE

    C++ 34 7

  5. ROART ROART Public

    Range Optimized Adaptive Radix Tree

    C++ 25 13

  6. syscall_intercept syscall_intercept Public

    Forked from pmem/syscall_intercept

    The system call intercepting library

    C 23 3

Repositories

Showing 10 of 45 repositories
  • sglang Public Forked from sgl-project/sglang

    SGLang is a fast serving framework for large language models and vision language models.

    madsys-dev/sglang's past year of commit activity
    Python 1 Apache-2.0 9,714 0 5 Updated Sep 26, 2026
  • smart Public

    Scaling Up Memory Disaggregated Applications with SMART (ASPLOS 24): Predecessor of Mooncake TE

    madsys-dev/smart's past year of commit activity
    C++ 34 MIT 7 1 0 Updated Jul 23, 2026
  • tokenspeed Public Forked from lightseekorg/tokenspeed

    TokenSpeed is a speed-of-light LLM inference engine.

    madsys-dev/tokenspeed's past year of commit activity
    Python 1 MIT 362 0 0 Updated May 16, 2026
  • smg Public Forked from smg-project/smg

    Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across SGLang, vLLM, TRT-LLM, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant auth.

    madsys-dev/smg's past year of commit activity
    Rust 0 Apache-2.0 195 0 0 Updated May 3, 2026
  • DeepGEMM Public Forked from deepseek-ai/DeepGEMM

    DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

    madsys-dev/DeepGEMM's past year of commit activity
    Cuda 0 MIT 1,430 0 0 Updated Apr 24, 2026
  • flashinfer Public Forked from flashinfer-ai/flashinfer

    FlashInfer: Kernel Library for LLM Serving

    madsys-dev/flashinfer's past year of commit activity
    Python 0 Apache-2.0 1,605 0 0 Updated Apr 22, 2026
  • sglang-2 Public Forked from 00fish0/sglang

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

    madsys-dev/sglang-2's past year of commit activity
    Python 1 Apache-2.0 9,714 0 0 Updated Apr 3, 2026
  • xgrammar Public Forked from mlc-ai/xgrammar

    Fast, Flexible and Portable Structured Generation

    madsys-dev/xgrammar's past year of commit activity
    C++ 0 Apache-2.0 237 0 0 Updated Mar 27, 2026
  • TorchSpec Public Forked from lightseekorg/TorchSpec

    A PyTorch native library for training speculative decoding models

    madsys-dev/TorchSpec's past year of commit activity
    Python 0 MIT 67 0 0 Updated Mar 21, 2026
  • overlaybd Public Forked from containerd/overlaybd

    Overlaybd: a block based remote image format. The storage backend of containerd/accelerated-container-image.

    madsys-dev/overlaybd's past year of commit activity
    C++ 0 Apache-2.0 93 0 0 Updated Dec 24, 2025
View all repositories

Most used topics

bindings rust