Loading blogs...
Posts tagged Performance.
Workstation WSL Proxy: compile OpenResty once into bwalia/wslproxy-openresty, warm Buildx/GHA layers, extract on bare metal, prefer DEPLOY_MODE=code — and why AI-assisted delivery made this cross-cutting work finishable.
Workstation com turboalimentação LLMs: paginação PagedAttention para cache KV, serviço vLLM, Self-Debugging para agentes, taxas de token PowerInfer e cortes de memória EG-MLA — com compensações de produção.