esp0r
Follow
Starred repositories
Production-ready MoE load balancing via real-time expert replication
Orchestrate multiple coding agents from desktop and mobile
🚀 Efficient implementations for emerging model architectures
high-performance linear attention kernel library built on TileLang
A kernel library written in tilelang
Accelerating MoE with IO and Tile-aware Optimizations
FlashInfer: Kernel Library for LLM Serving
Another Mihomo GUI.
Advanced Subscription Manager for QX, Loon, Surge, Stash, Egern and Shadowrocket!
PTX ISA 9.1 documentation converted to searchable markdown. Includes Claude Code skill for CUDA development.
Minimalistic Android note taking App | Notally, but eXtended.
Control Claude Code remotely via email、discord、telegram. Start tasks locally, receive notifications when Claude completes them, and send new commands by simply replying to emails.
Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.
集找番、追番、看番的一站式弹幕追番平台，云收藏同步 (Bangumi)，离线缓存，BitTorrent，弹幕云过滤。100% Kotlin/Compose Multiplatform
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
Enjoy the magic of Diffusion models!
A pipeline parallel training script for diffusion models.
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Wan: Open and Advanced Large-Scale Video Generative Models