Skip to content

@flashinfer-ai FlashInfer

Change the repository type filter

All

    Repositories list

    14 repositories

    • flashinfer

      Public
      FlashInfer: Kernel Library for LLM Serving
      gpucudajitpytorchnvidiamoeattentionllm-inferencelarge-large-modelsdistributed-inference
      Cuda
      •
      Apache License 2.0
      •555•4k•225•64•Updated Nov 3, 2025Nov 3, 2025

    • flashinfer-bench

      Public
      Building the Virtuous Cycle for AI-driven LLM Systems
      Python
      •
      Apache License 2.0
      •12•77•2•3•Updated Nov 2, 2025Nov 2, 2025

    • whl

      Public
      Pre-built wheels for flashinfer python package.
      HTML
      •4•2•0•0•Updated Nov 2, 2025Nov 2, 2025

    • flashinfer-ai.github.io

      Public
      Project website of FlashInfer project
      SCSS
      •4•0•1•0•Updated Oct 22, 2025Oct 22, 2025

    • cubloaty

      Public
      a size profiler for cuda binary
      Python
      •
      Apache License 2.0
      •0•52•0•0•Updated Oct 7, 2025Oct 7, 2025

    • web-data

      Public
      Apache License 2.0
      •0•0•0•0•Updated Jun 25, 2025Jun 25, 2025

    • cutlass-viz

      Public
      Python
      •
      Apache License 2.0
      •3•64•0•0•Updated Apr 26, 2025Apr 26, 2025

    • tg4perfetto

      Public
      Simple python library for generating your own perfetto traces for your application. Can be used for both app instrumentation and custom trace generation (for your own purposes)
      Python
      •
      Apache License 2.0
      •6•1•0•0•Updated Apr 16, 2025Apr 16, 2025

    • flashinfer-nightly

      Public archive
      FlashInfer Nightly
      MIT License
      •1•6•0•0•Updated Apr 9, 2025Apr 9, 2025

    • performance-tracking

      Public
      Apache License 2.0
      •0•4•0•0•Updated Apr 2, 2025Apr 2, 2025

    • llm-based-compression

      Public
      Jupyter Notebook
      •0•2•0•0•Updated Jan 10, 2025Jan 10, 2025

    • debug-print

      Public
      Debug print operator for cudagraph debugging
      Cuda
      •2•14•1•1•Updated Aug 2, 2024Aug 2, 2024

    • llvm-project

      Public
      The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
      Other
      •15k•0•0•0•Updated Apr 21, 2024Apr 21, 2024

    • candle

      Public
      Minimalist ML framework for Rust
      Rust
      •
      Apache License 2.0
      •1.3k•0•0•0•Updated Mar 7, 2024Mar 7, 2024