Pinned Repositories
abi-compliance-checker
A tool for checking backward API/ABI compatibility of a C/C++ library
blis
BLAS-like Library Instantiation Software Framework
bolt
10x faster matrix and vector operations.
gemmlowp
Low-precision matrix multiplication
iree
👻
memperf
memory mountain on arm
mlas
tensorflow-lite-cpp-examples
Forked from TI Repo https://git.ti.com/git/apps/tensorflow-lite-examples.git
OpenBLAS
OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.
cpufp
A CPU tool for benchmarking the peak of floating points
craft-zhang's Repositories
craft-zhang/blis
BLAS-like Library Instantiation Software Framework
craft-zhang/distributed-llama-mpi
Run LLMs on weak devices or make powerful devices even more powerful by distributing the workload and dividing the RAM usage.
craft-zhang/gemmlowp
Low-precision matrix multiplication
craft-zhang/mlas
craft-zhang/stable-diffusion.cpp
Stable Diffusion in pure C/C++
craft-zhang/anthropic-tokenizer
Approximation of the Claude 3 tokenizer by inspecting generation stream
craft-zhang/coriander
Build NVIDIA® CUDA™ code for OpenCL™ 1.2 devices
craft-zhang/cpufp
A CPU tool for benchmarking the peak of floating points
craft-zhang/fish-speech
Brand new TTS solution
craft-zhang/gemma.cpp
lightweight, standalone C++ inference engine for Google's Gemma models.
craft-zhang/gpt-engineer
Specify what you want it to build, the AI asks for clarification, and then builds it.
craft-zhang/LivePortrait
Make one portrait alive!
craft-zhang/llm.c
LLM training in simple, raw C/CUDA
craft-zhang/micro-agent
An AI agent that writes (actually useful) code for you
craft-zhang/optimized-routines
Optimized implementations of various library functions for ARM architecture processors
craft-zhang/ppl.llm.kernel.cuda
craft-zhang/ppl.llm.serving
craft-zhang/ppl.nn
A primitive library for neural network
craft-zhang/ppl.pmx
craft-zhang/Qwen-Agent
Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.
craft-zhang/Rin
⚡️Rin 是一个基于 Cloudflare Pages + Workers + D1 + R2 全家桶的博客,无需服务器无需备案,只需要一个解析到 Cloudflare 的域名即可部署。
craft-zhang/seed-tts-eval
craft-zhang/sidellama
craft-zhang/StreamSpeech
StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
craft-zhang/tcmalloc
craft-zhang/tf-quant-finance
High-performance TensorFlow library for quantitative finance.
craft-zhang/the-super-tiny-compiler
:snowman: Possibly the smallest compiler ever
craft-zhang/triton-viz
craft-zhang/WhisperKit
On-device Inference of Whisper Speech Recognition Models for Apple Silicon
craft-zhang/XHS-Downloader
小红书链接提取/作品采集工具:提取账号发布、收藏、点赞作品链接;提取搜索结果作品、用户链接;采集小红书作品信息;提取小红书作品下载地址;下载小红书无水印作品文件!