pepesi
Follow
Stars
Alipay DeepLink + JSBridge Security Research - 17 Verified Vulnerabilities | 支付宝DeepLink安全研究 | Full Report: innora.ai/zfb
Training neural networks on Apple Neural Engine via reverse-engineered private APIs
An agentic skills framework & software development methodology that works.
NVSentinel is a cross-platform fault remediation service designed to rapidly remediate runtime node-level issues in GPU-accelerated computing environments
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
Kubernetes-native AI serving platform for scalable model serving.
Run Slurm on Kubernetes. A Slinky project.
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
A high-performance inference engine for LLMs, optimized for diverse AI accelerators.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…
一个持续更新的中文敏感词库，帮助开发者和内容审核者快速识别并过滤不当文本，即将迎来重大更新。
Ultra-high-performance, secure, all-in-one acceleration engine for developer resources
Next Generation Agentic Proxy for AI Agents and MCP servers
Declaratively deploy your Kubernetes manifests, Kustomize configs, and Charts as Helm releases. Generate all-in-one manifests for use with ArgoCD.
llm-d helm charts and deployment examples
Gateway API Inference Extension
The Cloud-Native API Gateway and AI Gateway
Achieve state of the art inference performance with modern accelerators on Kubernetes
The Web framework for perfectionists with deadlines.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
Go client to download AI-Models from Cozy Hub, Hugging Face Hub, and Civitai.
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.