-
kuaishou
- Beijing
- https://www.zhihu.com/people/chao-li-11
Lists (1)
Sort Name ascending (A-Z)
Stars
Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch
My learning notes/codes for ML SYS.
A fast communication-overlapping library for tensor/expert parallelism on GPUs.
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
A high-performance algorithmic trading platform and event-driven backtester
The modern cryptocurrency trading bot framework written in Go.
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
Qwen Code is a coding agent that lives in the digital world.
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.
Machine Learning Engineering Open Book
Prompts, workflows and more for agentic engineering
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
A set of coding style guidelines for Vibe Coding or SWE-Agents that maximize efficiency and improve human readability.
本仓库包含对 Claude Code v1.0.33 进行逆向工程的完整研究和分析资料。包括对混淆源代码的深度技术分析、系统架构文档,以及重构 Claude Code agent 系统的实现蓝图。主要发现包括实时 Steering 机制、多 Agent 架构、智能上下文管理和工具执行管道。该项目为理解现代 AI agent 系统设计和实现提供技术参考。
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
TradingAgents: Multi-Agents LLM Financial Trading Framework
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Chat-based SQL Client and Editor for the next decade
SuperSonic is the next-generation AI+BI platform that unifies Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.
AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.