sihouzi21c Goto Github PK

abseil-cpp

Abseil Common Libraries (C++)

ao

PyTorch native quantization and sparsity for training and inference

autodiffusion1

blis

BLAS-like Library Instantiation Software Framework

clblast

Tuned OpenCL BLAS

cpp-httplib

A C++ header-only HTTP/HTTPS server and client library

cpuinfo

CPU INFOrmation library (x86/x86-64/ARM/ARM64, Linux/Windows/Android/macOS/iOS)

cudnn-frontend

cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it

cutlass

CUDA Templates for Linear Algebra Subroutines

executorch

On-device AI across mobile, embedded and edge for PyTorch

fbgemm

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

fbjni

A library designed to simplify the usage of the Java Native Interface

flatbuffers

FlatBuffers: Memory Efficient Serialization Library

fmt

A modern formatting library

fp16

Conversion to/from half-precision floating point formats

fxdiv

C99/C++ header-only library for division via fixed-point multiplication by inverse

gemmlowp

Low-precision matrix multiplication

gloo

Collective communications library with various primitives for multi-machine training.

googletest

GoogleTest - Google Testing and Mocking Framework

ideep

Intel® Optimization for Chainer*, a Chainer module providing numpy like API and DNN acceleration using MKL-DNN.

ittapi

Intel® Instrumentation and Tracing Technology (ITT) and Just-In-Time (JIT) API

json

JSON for Modern C++

kineto

A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.

llama.onnx

LLaMa/RWKV onnx models, quantization and testcase

llava

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

llm4decompile

Reverse Engineering: Decompiling Binary Code with Large Language Models

mimalloc

mimalloc is a compact general purpose allocator with excellent performance.

nccl

Optimized primitives for collective multi-GPU communication

nnpack

Acceleration package for neural networks on multi-core CPUs

nvtx

The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resources in your applications.