Lists (3)
Stars
🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSy…
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
My learning notes for ML SYS.
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Here are my personal paper reading notes (including machine learning systems, AI infrastructure, and other interesting stuffs).
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
SGLang is a high-performance serving framework for large language models and multimodal models.
Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
std::tuple like methods for user defined types without any macro or boilerplate code
A high-performance, Redis-compatible database written in modern C++23.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
A high-throughput and memory-efficient inference and serving engine for LLMs
Seamless operability between C++11 and Python
A PyTorch coding practice platform — covering LLM, Diffusion, PEFT, and more A friendly environment to help you deeply understand deep learning components through hands-on practice. Like LeetCode, …
Simple PyTorch Tutorials Zero to ALL!
Porting liburing/io_uring to C++26 std::execution (stdexec)
CUDA Templates and Python DSLs for High-Performance Linear Algebra
Tensors and Dynamic neural networks in Python with strong GPU acceleration
A disruptor thread-synchronisation data structure for C++11.
`std::execution`, the standard C++ framework for asynchronous and parallel programming.
C++14 concurrent lock-free low-latency queue.
A General-purpose Task-parallel Programming System in C++