Pinned Repositories
sherpa-ncnn
Real-time speech recognition using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Raspberry Pi, VisionFive2, LicheePi4A etc.
asr-decode
从Kaldi中裁剪的轻量级语音识别解码推理框架,目前实现了MFCC+GMM+Viterbi,不依赖OpenFST、OpenBLAS等库
keras-yolo4
A Keras implementation of YOLOv4 (Tensorflow backend)
llama2-infer
从零实现一个深度学习推理框架的练手实验
rasa_bot
整理:基于Rasa-NLU和Rasa-Core的任务型ChatBot
XLNet-ChineseNER
Tensorflow solution of NER task Using BiLSTM-CRF model with CMU/Google XLNet
yolact
A simple, fully convolutional model for real-time instance segmentation.
Yolact-CoreML
Yolact for iOS implemented using CoreML.
YOLOv3-CoreML
YOLOv3 for iOS implemented using CoreML.
wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
Ma-Dan's Repositories
Ma-Dan/CUDA-Learn-Note
🎉CUDA 笔记 / 大模型手撕CUDA / C++笔记,个人笔记,更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.
Ma-Dan/llama.cpp
Port of Facebook's LLaMA model in C/C++
Ma-Dan/llama2.c-to-ncnn
A converter for llama2.c legacy models to ncnn models.
Ma-Dan/ChatLM-mini-Chinese
中文对话0.2B小模型(ChatLM-Chinese-0.2B),开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调。
Ma-Dan/QAnything
Question and Answer based on Anything.
Ma-Dan/llama2-infer
从零实现一个深度学习推理框架的练手实验
Ma-Dan/alphageometry
Ma-Dan/ChatGLM-MNN
Pure C++, Easy Deploy ChatGLM-6B.
Ma-Dan/ColossalAI
Making large AI models cheaper, faster and more accessible
Ma-Dan/DB-GPT
Revolutionizing Database Interactions with Private LLM Technology
Ma-Dan/fastllm
纯c++的全平台llm加速库,支持python调用,chatglm-6B级模型单卡可达10000+token / s,支持glm, llama, moss基座,手机端流畅运行
Ma-Dan/Fooocus
Focus on prompting and generating
Ma-Dan/hadoop-hive-spark-docker
Hadoop-Hive-Spark cluster + Jupyter on Docker
Ma-Dan/icefall
Ma-Dan/k2
FSA/FST algorithms, differentiable, with PyTorch compatibility.
Ma-Dan/libllm
Efficient inference of large language models.
Ma-Dan/llama2.c
Inference Llama 2 in one file of pure C
Ma-Dan/llm.c
LLM training in simple, raw C/CUDA
Ma-Dan/mamba-finetune
Ma-Dan/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Ma-Dan/Open-Sora-Plan
This project aim to reproducing Sora (Open AI T2V model), but we only have limited resource. We deeply wish the all open source community can contribute to this project.
Ma-Dan/PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
Ma-Dan/sherpa
Speech-to-text server framework with next-gen Kaldi
Ma-Dan/sherpa-ncnn
Real-time speech recognition using next-gen Kaldi with ncnn
Ma-Dan/tiny-gpu
A minimal GPU design in Verilog to learn how GPUs work from the ground up
Ma-Dan/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Ma-Dan/vtensor
Ma-Dan/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
Ma-Dan/WeTextProcessing
Text Normalization & Inverse Text Normalization
Ma-Dan/whisper
Robust Speech Recognition via Large-Scale Weak Supervision