Stars
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
Brave browser for Android, iOS, Linux, macOS, Windows.
JavaScript API for Chrome and Firefox
Fast, efficient, and scalable distributed map/reduce system, DAG execution, in memory or on disk, written in pure Go, runs standalone or distributedly.
A high-throughput and memory-efficient inference and serving engine for LLMs
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Ongoing research training transformer models at scale
Library for reading and processing ML training data.
kenmcmil / ivy
Forked from microsoft/ivyIVy is a research tool intended to allow interactive development of protocols and their proofs of correctness and to provide a platform for developing and experimenting with automated proof techniq…
A feature-rich command-line audio/video downloader
A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support
This OS Tutorial expands on the fundamental concepts covered in cfenollosa/os-tutorial and covers entering long mode on the x86_64 architecture. It also uses clang rather than relying on an externa…
A simple hobby operating system for the x86-64 architecture
LaTeX mappings for Font Awesome, the icons font
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
MAT: Mask-Aware Transformer for Large Hole Image Inpainting
ZIO — A type-safe, composable library for async and concurrent programming in Scala
Netty project - an event-driven asynchronous network application framework
Neon: Serverless Postgres. We separated storage and compute to offer autoscaling, code-like database branching, and scale to zero.