v3.36.0
rasbt/LLMs-from-scratchv3.36.0Aug 17, 2026by enfein
Upgrading?
AI Summary
A performance update for a server component focusing on faster user matching and reduced memory usage during encryption.
Key Highlights
- Accelerated server user match for new connections
- Reduced encryption memory allocation and GC pressure
New Features
- Faster user matching
- Lower encryption memory footprint
Full Release Notes
1. Accelerate server user match from incoming new connections (issue #273). 2. Reduce encryption memory allocation and GC pressure (issue #297). --- 1. 加快了代理服务器对新网络连接的用户匹配速度。 2. 减少了加密所需的内存分配,降低垃圾回收压力。
Related Repositories
lyogavin/airllm★ 40,153
AirLLM 2.8T LLM inference with single 4GB GPU
NirDiamant/RAG_Techniques★ 29,958
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
microsoft/OmniParser★ 25,539
A simple screen parsing tool towards pure vision based GUI agent
karpathy/nn-zero-to-hero★ 24,906
Neural Networks: Zero to Hero
NirDiamant/GenAI_Agents★ 24,653
50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.