Skip to content
All tags

#self-hosting

14 posts
tech deep-dive

What Is GPUtw.ai? Taiwan GPU Cloud, Short-Rental Compute, and Researcher Workflows

GPUtw.ai is a Taiwan-based short-rental GPU cloud. Its main value is not maximum scale, but Taiwan data centers, prepaid credits, Jupyter/ComfyUI/Ollama/vLLM templates, Vault storage, and team billing. Public information is enough for a service introduction, not enough for procurement or production endorsement.

ai guide 認識 AI 模型

Self-Hosting Open-Source LLMs: Framework Choice, Hardware Math, and When It Beats APIs

Open-source models now match closed-source on coding benchmarks, but self-hosting isn't just picking a model — vLLM handles high-concurrency production serving, SGLang is 29% faster on prefix-heavy workloads, Ollama is the local dev default, and llama.cpp runs on the least hardware. A100 cloud rentals run ~$1.4-2.2/hr; self-hosting breaks even at roughly 100M tokens/month.

How to Pick a Self-Hosted Inference Server: From Ollama to Xinference, Six Tools and Their Trade-Offs

Self-hosted inference servers fall into three layers: execution engine (llama.cpp), serving engine (vLLM, SGLang), and model management platform (Ollama, Xinference, Triton). Picking the right layer matters more than picking the right tool — ask where your bottleneck is before deciding where to add complexity.

Xinference: One Platform to Manage LLM, Embedding, Speech, and Image Models

Xinference wraps vLLM, SGLang, llama.cpp, Transformers, and MLX under a single management layer, using a Web UI and OpenAI-compatible API to manage LLMs, embedding, rerank, speech, and image models — suited for self-hosted deployments that need multiple model types to coexist. But the management layer's parsing logic also creates a larger attack surface than pure serving engines (CVE-2026-61539 is a case study).

Appwrite: A Self-Hostable BaaS for Auth, Databases, Storage, Functions, and Realtime

Appwrite combines Auth, TablesDB, Storage, Functions, Realtime, and Messaging behind consistent APIs; Cloud and self-hosted products resemble each other but have different operational ownership.

CapRover: Self-Hosted PaaS with Docker Swarm, Nginx, and Persistent Apps

CapRover wraps Docker Swarm, Nginx, and captain-definition in a simpler PaaS; stateless apps scale, while local persistent apps remain pinned to one node.

Coolify: Control Planes, Docker Servers, and the Self-Hosted PaaS Boundary

Coolify controls Docker, proxies, and resources on your servers over SSH; deployment gets easier, but OS, security, capacity, data backup, and recovery remain yours.

Dokku: Turning One Docker Host into a Git-Push PaaS

Dokku combines a Git receiver, buildpacks or Dockerfiles, process models, Nginx, and plugins for a single-host Heroku workflow; simplicity comes from narrow orchestration scope.

Dokploy: Self-Hosted PaaS with Applications, Compose, Remote Servers, and Swarm

Dokploy supports single-container Applications and Compose or Stack, while treating one host, independent remote servers, and a Swarm cluster as distinct topologies.

Hetzner Cloud: Cheap VMs Mean Owning the Entire Operating System

Hetzner Cloud offers lean IaaS through servers, networks, volumes, load balancers, and firewalls; its price advantage is real only after patches, HA, backups, egress, and on-call are counted.

Kamal: Docker Deployment Without a Resident Control Plane

Kamal deploys immutable images from an operator over SSH and switches traffic through kamal-proxy; it is not a scheduler and does not operate hosts or data.

PocketBase: A Single-Binary Backend with SQLite, Auth, and Realtime

PocketBase packages SQLite, collections, Auth, file storage, SSE realtime, and an admin UI into a small executable; deployment is easy, but single-host and pre-v1 compatibility limits matter.

Proxmox VE: Combining KVM, LXC, Clusters, Ceph, and Backups On-Premises

Proxmox VE integrates VMs, containers, clusters, HA, storage, and backup; it simplifies virtualization management while hardware, quorum, networks, capacity, and DR remain yours.

vLLM: The Default Choice for Self-Hosted Inference — and When It's Over-Engineering

vLLM is the de facto standard for self-hosted LLM inference (89,470 GitHub stars, verified 2026-08-21), built on managing the KV cache the way an OS manages paged memory. But the selection question isn't how fast it is — it's your GPU utilization. Using Red Hat's measured 793 output tokens/second, a fully saturated A100 costs roughly $0.70 per million output tokens; at 10% utilization that becomes $7, more than most cloud APIs.