№ 02 / SUMMARIES

#deployment

Every summary, chronological. Filter by category, tag, or source from the rail.

Tag · #deployment
DAY 01July 28, 2026 JUL 28 · 20261 SUMMARIES
IBM TechnologyAI & LLMs

Choosing Between Llama.cpp and vLLM for Local LLM Inference

Llama.cpp is optimized for running LLMs on consumer hardware via quantization, while vLLM is designed for high-throughput production environments using techniques like continuous batching and PagedAttention.

IBM Technology
DAY 02June 6, 2026 JUN 6 · 20261 SUMMARIES
MarkTechPostAI & LLMs

Deploying Qualcomm AI Hub Models: From PyTorch to On-Device

A practical guide to using the Qualcomm AI Hub SDK to load, test, and deploy models like MobileNet-V2 and YOLOv7, including cloud-based hardware profiling and TFLite compilation.

MarkTechPost
DAY 03February 13, 2018 FEB 13 · 20181 SUMMARIES
__oneoff__DevOps & Cloud

Rainbow Deploys: Git SHA Kubernetes for Stateful Drains

For stateful services like websocket backends needing hours to drain connections, deploy Kubernetes with git SHA-named Deployments, switch Service selectors to new ones, and manually delete old after traffic burns down—avoids mass reconnects unlike rolling updates.

__oneoff__

Showing 4 of 4