lyan
CodeFun
  • Home
  • Archives
  • About
  • Links
EN 中文 日本語
  1. Home
  2. Archives

Hands on DSH

2026-09-14

A technical guide to DeepSeek Harness architecture, implementation, deployment, usage, and its differences from OpenClaw.

OpenClaw DeepSeek Harness DSH AI Agents Agent Architecture
Read More

Dive into the Agent Loop

lyan 2026-08-14

A practical breakdown of the agent loop: the roles of models, MCP servers, and clients, plus Skills, multi-agent systems, and context isolation.

Agent MCP LLM Multi-agent Architecture
Read More

How uv Works: Python Environments, Dependency Resolution, and Caching

lyan 2026-07-15

A practical explanation of uv's internal workflow, from Python selection and PubGrub resolution to lockfiles, caching, virtual environments, and uv run.

Python uv Developer Tools Dependency Management
Read More

Cross-Attention in Multimodal AI: When One Stream Needs to Read Another

lyan 2026-07-05

A practical guide to cross-attention, from Q/K/V to Stable Diffusion’s text-conditioned U-Net and cross-modal dimension design.

AI Transformer Cross-Attention Multimodal Stable Diffusion
Read More

LFT and Topology Exports in InfiniBand: Diagnose the Fabric Without Expanding the Attack Surface

lyan 2026-06-26

A practical, evidence-based framework for collecting and handling InfiniBand LFT, topology, and UFM snapshot data without exposing the management plane.

Network NVIDIA RDMA InfiniBand HPC Security UFM
Read More
  • 1
  • Next

Search

Top Posts

  • Step into the world of ARM Server
  • Running Debian ARM64 on QEMU with UEFI

Hot Posts

  • A Comprehensive Guide to Multi-Node, Multi-GPU NVIDIA GPU Fabric Deployment
  • Hands on DSH
  • Dive into the Agent Loop
  • How uv Works: Python Environments, Dependency Resolution, and Caching
  • Cross-Attention in Multimodal AI: When One Stream Needs to Read Another
  • LFT and Topology Exports in InfiniBand: Diagnose the Fabric Without Expanding the Attack Surface
  • The Decision Engine Behind Fused Attention: How Transformer Engine Orchestrates cuDNN on Blackwell
  • Megatron-Bridge in Practice: A Production 101 Guide to the Nemotron, Megatron-Core, and Transformer Engine Stack
  • FMHA 101: From Transformer Attention to a CUDA Flash Attention Kernel

Recent Posts

  • Hands on DSH
  • Dive into the Agent Loop
  • How uv Works: Python Environments, Dependency Resolution, and Caching
  • Cross-Attention in Multimodal AI: When One Stream Needs to Read Another
  • LFT and Topology Exports in InfiniBand: Diagnose the Fabric Without Expanding the Attack Surface
  • The Decision Engine Behind Fused Attention: How Transformer Engine Orchestrates cuDNN on Blackwell
  • Megatron-Bridge in Practice: A Production 101 Guide to the Nemotron, Megatron-Core, and Transformer Engine Stack
  • FMHA 101: From Transformer Attention to a CUDA Flash Attention Kernel
  • Enroot + Pyxis + SPANK: A Practical Architecture and Operations Guide for Slurm Containers

Tag Cloud

Linux (61) XEN (29) Life (27) Memory (24) Virtualization (23) Diary (21) C/C++ (19) QEMU (17) test (15) CPU (14) NVIDIA (13) InfiniBand (11) AI (11) Interest (11) Algorithm (11) VisualStudio (11) HPC (10) GPU (10) KVM (10) Transformer (9) eBPF (8) MFC (8) OpenClaw (7) Debian (7) LLM (6) Engine (6) MLOps (6) Security (6) TorchDynamo (6) PyTorch (6) CUDA (6) programming (6)
lyan
CodeFun

©2026 xryan.net.

Code all fun things in the world by Leon.

  • Links
  • About Us
  • Feedback
QR Code
Scan to follow