Loading blogs...
Posts tagged AI.
Workstation on turbocharging LLMs: PagedAttention paging for KV cache, vLLM serving, Self-Debugging for agents, PowerInfer token rates, and EG-MLA memory cuts — with production trade-offs.
Workstation on async Rust blocking, Rayon for CPU-bound work, and why Rust fits modern APIs, edge, agents, and CI/CD — inspired by Alice Ryhl’s Rayon guidance.
Workstation WSL Proxy (WSLProxy) is a complete API gateway and CDN edge: live routing, WAF, cache, multi-POP DNS, MCP — with Agents Gateway and MCP Gateway in progress.
How a wise developer works a new project — brainstorm, discuss, prototype, diagram, propose, ADR, PR, GitOps — plus Review Bots and Workstation multi-agent teams.
The wise path for a new project: brainstorm, teammate discussion, prototypes, diagrams, proposals, ADRs, small PRs with Review Bots, and GitOps for production-grade quality.
Technical Workstation brief on deep learning: gradient-trained deep nets, discriminative vs generative models, task metrics, and Bedrock vs Kubernetes serving.
I unboxed a Mac Studio M4 Max with 128 GB unified memory and 40 GPU cores, installed Ollama, ran Llama 3.1 8B locally, and built a private RAG pipeline - all on one quiet, 6.48 W idle desk-side box.
Discover how Transformer architecture revolutionized AI, enabling breakthroughs in natural language processing, computer vision, and solving complex real-world problems.