ajunlonglive

Pinned Repositories

3FS
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
Language:C++00
3rd
Language:C0 1 00
accelerate
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
Language:Python0 1 00
acidcamGL
OpenGL-based version of Acid Cam controlled with a computer keyboard for live visuals to stream online with OBS.
Language:C++0 1 00
addons-1
Useful extra functionality for TensorFlow 2.x maintained by SIG-addons
Language:Python0 2 00
AdvBox
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.
Language:Jupyter Notebook0 1 00
adversarial-attacks-pytorch
PyTorch implementation of adversarial attacks.
Language:Python0 1 00
agents
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
Language:Python0 1 00
AI-For-Beginners
12 Weeks, 24 Lessons, AI for All!
Language:Jupyter Notebook00
optimum
🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools
Language:Python1 1 00

ajunlonglive's Repositories

ajunlonglive/cosmopolitan
build-once run-anywhere c library
Language:C1 0
ajunlonglive/curl-c
A command line tool and library for transferring data with URL syntax, supporting DICT, FILE, FTP, FTPS, GOPHER, GOPHERS, HTTP, HTTPS, IMAP, IMAPS, LDAP, LDAPS, MQTT, POP3, POP3S, RTMP, RTMPS, RTSP, SCP, SFTP, SMB, SMBS, SMTP, SMTPS, TELNET, TFTP, WS and WSS. libcurl offers a myriad of powerful features
Language:C0 0
ajunlonglive/exvllm
vllm混合推理扩展插件，支持多NUMA混合推理，单卡推理Qwen3-Next模型可达1000+ prefill
ajunlonglive/fast-hadamard-transform
Fast Hadamard transform in CUDA, with a PyTorch interface
ajunlonglive/fastllm
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。
Language:C++
ajunlonglive/FFmpeg
Mirror of https://git.ffmpeg.org/ffmpeg.git
Language:C1 0
ajunlonglive/firefox-ios
Firefox for iOS
Language:Swift1 0
ajunlonglive/flash-attention
Fast and memory-efficient exact attention
ajunlonglive/flashinfer
FlashInfer: Kernel Library for LLM Serving
ajunlonglive/ik_llama.cpp
llama.cpp fork with additional SOTA quants and improved performance
ajunlonglive/janus-gateway
Janus WebRTC Server
ajunlonglive/lktransformers
full support for numa
Language:Python
ajunlonglive/llama_sdk
lcpp is a dart implementation of llama.cpp used by the mobile artificial intelligence distribution (maid)
ajunlonglive/lmms
Cross-platform music production software
Language:C++
ajunlonglive/lvgl
Powerful and easy-to-use embedded GUI library with many widgets, advanced visual effects (opacity, antialiasing, animations) and low memory requirements (16K RAM, 64K Flash).
Language:C
ajunlonglive/Lvllm
vllm full numa support extention for moe model
ajunlonglive/minio
High Performance, Kubernetes Native Object Storage
Language:Go
ajunlonglive/mpv
🎥 Command line video player
Language:C
ajunlonglive/MuseScore
MuseScore is an open source and free music notation software. For support, contribution, bug reports, visit MuseScore.org. Fork and make pull requests!
ajunlonglive/obs-studio
OBS Studio - Free and open source software for live streaming and screen recording
Language:C
ajunlonglive/radare2
UNIX-like reverse engineering framework and command-line toolset
Language:C
ajunlonglive/react-bits
An open source collection of animated, interactive & fully customizable React components for building stunning, memorable user interfaces.
Language:JavaScript
ajunlonglive/reactos
A free Windows-compatible Operating System
Language:C1 0
ajunlonglive/redpanda
Redpanda is a streaming data platform for developers. Kafka API compatible. 10x faster. No ZooKeeper. No JVM!
Language:C++
ajunlonglive/RedPanda-CPP
A light-weight C/C++ IDE based on Qt
Language:C++1 0
ajunlonglive/scrcpy
Display and control your Android device
Language:C
ajunlonglive/sglang
SGLang is a fast serving framework for large language models and vision language models.
Language:Python
ajunlonglive/TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in performant way.
ajunlonglive/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Language:Python
ajunlonglive/yyjson
The fastest C JSON library
Language:C