{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "infermatrixlab-vllm-rlt--benchmark-serving-on-own-gpus",
 "repo": "InferMatrixLab/vllm-rlt",
 "repo_url": "https://github.com/InferMatrixLab/vllm-rlt",
 "repo_slug": "infermatrixlab-vllm-rlt",
 "title": "Benchmark depth-aware serving on your own GPUs",
 "page_title": "How to benchmark depth-aware serving on your own GPUs with vLLM RLT",
 "summary": "Reproduce the published baseline protocol on your hardware before choosing a serving layout.",
 "who": "Infrastructure lead deciding whether to run one replica or split prefill and decode pools across several GPUs on one host.",
 "problem": "Published numbers come from specific hardware and workloads, so the team needs its own measurements before committing to a layout.",
 "outcome": "A short report comparing throughput and latency for your GPU setup against the recorded baselines, with the workload described.",
 "steps": [
  "Run `uv pip install -e .` from the repository root and confirm the server starts on your GPUs.",
  "Read the performance baselines in the README and the linked PR #30 and PR #31 protocols to match concurrency, output length, and prompt length.",
  "Read the prefill/decode disaggregation notes in the documentation to plan a P and D pool layout on one host.",
  "Run the same fixed-arrival or concurrency workload against one replica and against a split layout, recording TTFT, ITL, and throughput. (inferred, check the README)",
  "Write a summary that states the hardware, model, feature flags, and the measured percentage changes."
 ],
 "agent_prompt": "In the vllm-rlt repository, follow the protocol in the linked PR #30 and PR #31 to benchmark Ouro-1.4B BF16 on <your GPU setup> with a single replica and with a split prefill/decode layout. Output a table of throughput, TTFT, and ITL for each layout. Verify that the workload settings match across both runs.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "180 minutes",
 "basis": "readme",
 "caveat": "The README says the published results are workload-specific and not a fresh v0.1.0 benchmark, so your numbers will only be comparable if the protocol matches exactly.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "Linux machine with an NVIDIA GPU and a CUDA-enabled PyTorch installation compatible with the hardware",
  "Python 3.10 or newer and PyTorch 2.5 or newer",
  "uv installed to run the install command from the repository root",
  "Access to download the chosen checkpoint, such as ByteDance/Ouro-1.4B"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.7,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/infermatrixlab-vllm-rlt/benchmark-serving-on-own-gpus/",
 "md": "https://dedupedai.com/use-cases/infermatrixlab-vllm-rlt/benchmark-serving-on-own-gpus/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/infermatrixlab-vllm-rlt--benchmark-serving-on-own-gpus.json",
 "api_version": "v1"
}