-
University of California - Los Angeles
- in/junxiao-zhao-746512250
Highlights
- Pro
Stars
DeepEP: an efficient expert-parallel communication library
Ongoing research training transformer models at scale
fanshiqing / grouped_gemm
Forked from tgale96/grouped_gemmPyTorch bindings for CUTLASS grouped GEMM.
HuggingFace conversion and training library for Megatron-based models
FreeProxy: Collecting free proxies from internet. (海量全球免费代理,20+代理源,爬虫与数据分析必备。)
There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable an…
A privacy-first, open-source platform for knowledge management and collaboration. Download link: http://github.com/logseq/logseq/releases. roadmap: https://discuss.logseq.com/t/logseq-product-roadm…
MicroPython - a lean and efficient Python implementation for microcontrollers and constrained systems
Recent LLM-Based Time Series Forecasting Models with Code
An expressive, semi-modular, and comprehensive physical modeling/waveguide synthesizer.
ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
FinRL®: Financial Reinforcement Learning. 🔥
Minimal reproduction of DeepSeek R1-Zero
verl: Volcano Engine Reinforcement Learning for LLMs
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
Synthesizer plug-in (previously released as Vember Audio Surge)
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
Third-party audio effects plugins as differentiable layers within deep neural networks.
Awesome-llm-role-playing-with-persona: a curated list of resources for large language models for role-playing with assigned personas
jmriebold / BoilerPy3
Forked from mercuree/BoilerPyPython port of Boilerpipe library
fast python port of arc90's readability tool, updated to match latest readability.js!
Built-in Mail & Calendars app clone for Windows.
Production-ready platform for agentic workflow development.

