Lists (4)
Stars
The official PyTorch implementation of "Sketch and Paint: A Structural-Temporal Aware Refinement Network for Fine-grained Crop Mapping on Satellite Image Time Series".
Official repository for paper Routing-Free Mixture-of-Experts.
A from-scratch Prefill/Decode disaggregation inference engine for LLMs
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
Official codebase for the MLSys 2026 paper "IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference". It enables high-fidelity and high-speed LLM/ViT deployment on ARM CPUs.
A CLI tool to switch and manage Codex accounts
An intelligent conversational agent for remote sensing image processing, enabling complex geospatial tasks through natural language
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build, Muse Code, Devin as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini Series, GPT Series, Grok Se…
最好用的 sing-box 一键安装脚本 & 管理脚本，自动创建 REALITY 协议；支持 TUIC，Trojan，Hysteria2 等所有常见的协议
Algorithm powering the For You feed on X
SGLang is a high-performance serving framework for large language models and multimodal models.
Paper reading and discussion notes, covering AI frameworks, distributed systems, cluster management, etc.
一些关于目标检测的脚本和改进思路代码，详细请看readme.md
A unified inference and post-training framework for accelerated video generation.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…
A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.
通过Anki Fsrs算法速成力扣：自动推荐题目，每日复习（支持导入外部题目：手撕、洛谷、codeforce、牛客、一题多解）。Master LeetCode via Anki Fsrs：auto-recommend problems, review daily.
🔥 Latest advances in Video Object Segmentation (VOS) – papers, datasets, and projects.
[NeurIPS 2021] Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
Summary of some awesome work for optimizing LLM inference
Development repository for the Triton language and compiler
A transparent, in-container GPU resource controller that enforces memory and compute limits by intercepting CUDA calls without application or driver changes.
Solve Visual Understanding with Reinforced VLMs