DeepCache

aisimulate 开源

不占 GPU 也能预测大模型服务性能并搜配置

AISimulate predicts LLM serving behavior and searches for strong deployment configur···

pai 开源

管好 GPU 集群，让 AI 训练快人一步

Resource scheduling and cluster management for AI

statewave 开源

给AI智能体装上可追溯的长期记忆，告别查询式检索

Open-source memory runtime for AI agents — reproducible, provenance-tagged context ···

sglang 开源

让大模型服务更快更省，复杂提示词场景吞吐翻倍

SGLang is a high-performance serving framework for large language models and multimo···

grps_trtllm 开源

用 C++ 榨干 GPU，OpenAI 服务比 vLLM 更快

Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance O···

context-keeper 开源

给大模型装上持久记忆，告别上下文丢失

LLM-Driven Intelligent Memory & Context Management System （AI记忆管理与智能上下文感···

opentraces 开源

给 AI Agent 装上黑匣子，完整记录每一步操作，调试审计不再抓瞎。

A local-first evidence layer for agent work, capturing what the agent sees, does, an···

kronk 开源

Go 项目一键接入本地大模型、语音和图像生成

Go With Your Own Intelligence! Use Go for hardware accelerated local inference with ···

redis-llm 开源

用 Redis 给 LLM 装个长期记忆，轻松访问私有数据

redis-llm integrates LLM with Redis. It can help LLM to access private data, and rem···