fengyuentau

core

:house_with_garden: Open source home automation that puts local control and privacy first.

folly

An open-source C++ library developed and used at Facebook.

vllm

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

abseil-cpp

Abseil Common Libraries (C++)

triton

Development repository for the Triton language and compiler

runner-images

GitHub Actions runner images

yolov9

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

oneTBB

oneAPI Threading Building Blocks (oneTBB)

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

EfficientSAM

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

amx

Apple AMX Instruction Set

libxsmm

Library for specialized dense and sparse matrix operations, and deep learning primitives.

intel-graphics-compiler

cpufp

A CPU tool for benchmarking the peak of floating points

DCNv4

[CVPR 2024] Deformable Convolution v4

onnxruntime-genai

Generative AI extensions for onnxruntime

clpeak

A tool which profiles OpenCL devices to find their peak capacities

BitBLAS

BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

OpenCL-Docs

OpenCL API, OpenCL C, Extensions, SPIR-V Environment Specs, Ref page, and C++ for OpenCL doc sources.

clvk

Implementation of OpenCL 3.0 on Vulkan

portBLAS

An implementation of BLAS using the SYCL open standard.

llm-export

llm-export can export llm model to onnx.

OnnxSlim

A Toolkit to Help Optimize Large Onnx Model

OpenCL-Registry

OpenCL API and Extension Registry.

portDNN

portDNN is a library implementing neural network algorithms written using SYCL

metrics-discovery

neural-compressor

Model compression for ONNX

tflite-vx-delegate

Tensorflow Lite external delegate based on TIM-VX

AML_NN_SDK

mediapipe_cmake

Try to reproduce mediapipe with OpenCV_lite and MNN.