SungBalance/sdprofiler

stars

commits

Python

primary language

Oct 20, 2025

updated

README

SDProfiler

LLM inference engine using flashinfer kernels

Installation

git clone https://github.com/SungBalance/SDProfiler.git
cd SDProfiler
docker build -t sdprofiler:0.1 .    # It tasks ~25 min
./run_docker.sh
pip install -e .

Contributors

SungBalance

3 commits

Similar repos

mlsys-seo/multisd-llm-engine

ResponsibleAILab/S3LLM

tjluyao/fastSD

Tencent/KsanaLLM

549

flashinfer-ai/flashinfer

FlashInfer: Kernel Library for LLM Serving

6,375

OpenBMB/cpm.cu

CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device…

241

infinigence/Semi-PD

A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained…

131

Snowflake-AI-Research/fastkernels

Languages

Python

98.1%