{
 "schema_version": 1,
 "generated": "2026-10-26",
 "id": "azrtydxb-fastllm-proxy--spill-local-gpu-traffic-to-cloud",
 "repo": "azrtydxb/Fastllm-proxy",
 "repo_url": "https://github.com/azrtydxb/Fastllm-proxy",
 "repo_slug": "azrtydxb-fastllm-proxy",
 "title": "Use local GPUs first and spill to the cloud when busy",
 "page_title": "How to use local GPUs first and spill to the cloud when busy with Fastllm Proxy",
 "summary": "Write first-match routing rules so requests go to your local model until it is full, then to a cloud provider.",
 "who": "An ML infra engineer with a few GPUs who wants cloud only for overflow.",
 "problem": "Static routing either overloads local GPUs or wastes cloud spend.",
 "outcome": "Traffic that stays local while capacity allows and overflows automatically.",
 "steps": [
  "Define a local backend and a cloud provider",
  "Add a rule at position 0 with max_inflight_per_backend targeting the local model",
  "Add a rule at position 1 targeting the cloud provider",
  "Load test and watch where requests land"
 ],
 "agent_prompt": "Configure fastllm-proxy routing so <local model> takes up to 2 in-flight requests per backend and extra requests go to <cloud provider>. Send 10 parallel requests and report how many hit each target.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "45 minutes",
 "basis": "readme",
 "caveat": "Rules are evaluated in position order, so a broad rule placed first will shadow later ones.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "rust",
 "requirements": [
  "Docker and Docker Compose",
  "At least one inference backend or provider key"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/azrtydxb-fastllm-proxy/spill-local-gpu-traffic-to-cloud/",
 "md": "https://dedupedai.com/use-cases/azrtydxb-fastllm-proxy/spill-local-gpu-traffic-to-cloud/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/azrtydxb-fastllm-proxy--spill-local-gpu-traffic-to-cloud.json",
 "api_version": "v1"
}