linxin2429

generative-ai-for-beginners

18 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

tinygrad

You like pytorch? You like micrograd? You love tinygrad! ❤️

awesome-deep-learning

A curated list of awesome Deep Learning tutorials, projects and communities.

pingora

A library for building fast, reliable and evolvable network services.

pykan

Kolmogorov Arnold Networks

DeepLearningExamples

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

triton

Development repository for the Triton language and compiler

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

mlops-zoomcamp

Free MLOps course from DataTalks.Club

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

juicefs

JuiceFS is a distributed POSIX file system built on top of Redis and S3.

quiche

🥧 Savoury implementation of the QUIC transport protocol and HTTP/3

micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

LWM

FasterTransformer

Transformer related optimization, including BERT, GPT

OOTDiffusion

Official implementation of OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on

MiniCPM

MiniCPM-2B: An end-side LLM outperforming Llama2-13B.

dlssg-to-fsr3

Adds AMD FSR 3 Frame Generation to games by replacing Nvidia DLSS-G Frame Generation (nvngx_dlssg).

ml-interviews-book

https://huyenchip.com/ml-interviews-book/

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

tvm_mlir_learn

compiler learning resources collect.

VideoPipe

跨平台的视频结构化（视频分析）框架，觉得有帮助的请给个星星 : ) 。**VideoPipe下一版本正在开发中，在保证跨平台、易上手的前提下，预计性能直逼deepstream等各硬件平台官方框架**。

micro-arch-training

How to make undergraduates or new graduates ready for advanced computer architecture research or modern CPU design

optd

CMU-DB's Cascades optimizer framework

CS149-parallel-computing

Learning materials for Stanford CS149 : Parallel Computing

CUDATutorial

A CUDA tutorial to make people learn CUDA program from 0

core

The core library and APIs implementing the Triton Inference Server.