Lists (9)
Stars
Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”
[Notice] The repo temporarily locked while ownership transfer. in the meantime we maintain on here: https://github.com/ultraworkers/claw-code-parity. The fastest repo in history to surpass 100K sta…
FlashSampling: Fast and Memory-Efficient Exact Sampling (https://huggingface.co/papers/2603.15854)
An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".
🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.
Awesome LLM pruning papers all-in-one repository with integrating all useful resources and insights.
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
In the AI era, why can't everyone be a Principal Investigator?
A PyTorch native platform for training generative AI models
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Accelerating MoE with IO and Tile-aware Optimizations
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
AI agents running research on single-GPU nanochat training automatically
Terminal UI for NVIDIA Nsight Systems profiles — timeline viewer, kernel navigator, NVTX hierarchy
This repository compiles a list of papers related to the application of video technology in the field of robotics! Star⭐ the repo and follow me if you like what you see🤩.
Helios: Real Real-Time Long Video Generation Model
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
45 tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script, cutting the system prompt in half, using Gemini CLI as Claude Code's minion, and Cla…
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
Qwen3.5 is the large language model series developed by Qwen team, Alibaba Cloud.
2026年稳定高速VPN推荐：40款性价比翻墙梯子完全指南，翻墙梯子，电脑、手机、iOS、安卓、windows、Mac、Linux、路由器翻墙、科学上网、解锁YouTube、Netflix、TikTok、ChatGPT、bilibili港澳台。科学上网、梯子、VPN测评，适用Clash、V2ray、小火箭、sing-box等客户端