Stars
Scrum poker for Jira Cloud backlogs: one lightweight container, no session storage
Model-agnostic ledger of avoidable agent token spend: name why prompt cache misses, price the miss, prove fixes without losing task success.
kleinblue4 / AIInfraGuide
Forked from caomaolufei/AIInfraGuideAI Infra 全栈从0入门学习资料:https://caomaolufei.github.io/AIInfraGuide/
Lightweight, Modular, Kubernetes-native AI serving platform for scalable model serving.
Cursor plugin specification and official plugins
FelipePrado0 / SpartanPort
Forked from Supermedo/bloodborne_pcSpartanPort: unofficial PC port of God of War III Remastered (PS4) for Windows and Linux (AppImage). Original x86-64 code runs directly on the CPU with a custom runtime; graphics use shadPS4's Vulk…
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
LeetCode for PyTorch — 65 ML/AI interview problems from real interviews at Google, Meta, Anthropic. Jupyter notebooks, an auto-grader, and an MCP AI tutor.
TokenSpeed is a speed-of-light LLM inference engine.
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.
State of the art inference performance with modern accelerators on Kubernetes
FlashInfer: Kernel Library for LLM Serving
A plugin to edit and view Excalidraw drawings in Obsidian
𝐍𝐈𝐖 𝐀𝐩𝐩𝐫𝐨𝐯𝐚𝐥 𝐢𝐧 𝐎𝐧𝐞 𝐖𝐞𝐞𝐤 [Latex Template]
Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
Lightweight coding agent that runs in your terminal
分享AI Infra知识&代码练习:PyTorch、vLLM/SGLang、slime/vime框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等
Solutions for Object Oriented Design Problems