Pinned Repositories
cutlass-viz
debug-print
Debug print operator for cudagraph debugging
flashinfer
FlashInfer: Kernel Library for LLM Serving
flashinfer-nightly
FlashInfer Nightly
llm-based-compression
llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
performance-tracking
tg4perfetto
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)
web-data
whl
Pre-built wheels for flashinfer python package.
FlashInfer's Repositories
flashinfer-ai/flashinfer
FlashInfer: Kernel Library for LLM Serving
flashinfer-ai/cutlass-viz
flashinfer-ai/debug-print
Debug print operator for cudagraph debugging
flashinfer-ai/flashinfer-nightly
FlashInfer Nightly
flashinfer-ai/performance-tracking
flashinfer-ai/llm-based-compression
flashinfer-ai/whl
Pre-built wheels for flashinfer python package.
flashinfer-ai/llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
flashinfer-ai/tg4perfetto
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)
flashinfer-ai/candle
Minimalist ML framework for Rust
flashinfer-ai/flashinfer-ai.github.io
Project website of FlashInfer project
flashinfer-ai/web-data