shihongzhi
Follow
Starred repositories
how to optimize some algorithm in cuda.
📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
verl: Volcano Engine Reinforcement Learning for LLMs
Fully open reproduction of DeepSeek-R1
Rhino is an open-source implementation of JavaScript written entirely in Java
A runtime for writing reliable asynchronous applications with Rust. Provides I/O, networking, scheduling, timers, ...
Chromium Embedded Framework (CEF). A simple framework for embedding Chromium-based browsers in other applications.
A miniature model of the Typescript compiler, intended to teach the structure of the real Typescript compiler
A repo containing notes about the TypeScript Compiler codebase
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
JavaScript syntax tree transformer, nondestructive pretty-printer, and automatic source map generator
Statoscope is a toolkit to analyze and validate webpack bundle
Netease Youdao's open-source embedding and reranker models for RAG products.
Distributed LLM and StableDiffusion inference for mobile, desktop and server.
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)