BBuf
Follow
Lists (1)
Stars
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
PolyArch / oh-my-humanize
Forked from can1357/oh-my-pi⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and agentized workflows
[MLSys 26] 🥇 Solution for Gated Delta Net Track of MLSys 26 Flash infer competition
SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models
Skills for writing tilelang and debugging with CUDA toolkits.
Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.
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
Efficient and unified implementations for TopK-based sparse attention
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…
Information collection for the Happy Horse AI video generator model. Official demo and updates at happyhorses.io.
PTX ISA 9.1 documentation converted to searchable markdown. Includes Claude Code skill for CUDA development.
Agentic Kernel Optimization for All — automated GPU kernel optimization for any kernel, any hardware, any language
Autonomous GPU kernel optimization system driven by AI agents.
A PyTorch native platform for training generative AI models
Automated CUDA kernel performance diagnostics from NVIDIA Nsight Compute (NCU) CSV exports.
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
Terminal UI for NVIDIA Nsight Systems profiles — timeline viewer, kernel navigator, NVTX hierarchy
Humanizer 的汉化版本，Claude Code Skills，旨在消除文本中 AI 生成的痕迹。
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
An agentic skills framework & software development methodology that works.
FlashInfer: Kernel Library for LLM Serving