{
 "schema_version": 1,
 "generated": "2026-10-24",
 "id": "deepseek-ai-deepinfer--benchmark-prefill-and-decode-throughput",
 "repo": "deepseek-ai/DeepInfer",
 "repo_url": "https://github.com/deepseek-ai/DeepInfer",
 "repo_slug": "deepseek-ai-deepinfer",
 "title": "Reproduce Deep Infer prefill and decode benchmarks",
 "page_title": "How to reproduce Deep Infer prefill and decode benchmarks with Deep Infer",
 "summary": "Run the sweep script to measure prefill and decode performance on SM100 GPUs.",
 "who": "An infrastructure engineer comparing serving hardware or validating the published Deep Infer performance numbers.",
 "problem": "Published benchmark numbers are only useful if you can rerun them on your own setup.",
 "outcome": "Your own prefill and decode benchmark results that you can compare with the published charts.",
 "steps": [
  "Complete the build steps so Deep Infer runs on your SM100 GPUs.",
  "Read the README note that prefill was measured on 4 SM100 GPUs and decode on 64, each within one scale-up domain.",
  "Run the sweep script at `examples/sweep/run_sweep.sh`.",
  "Save the output and compare the prefill and decode results with the charts in the README."
 ],
 "agent_prompt": "In the DeepInfer repo, run examples/sweep/run_sweep.sh on <number of GPUs> SM100 GPUs and save the output to <output path>. Report the prefill and decode results. Verify that the GPU count matches the layout the README describes before comparing with the published charts.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "3 hours",
 "basis": "readme",
 "caveat": "The published numbers used 4 GPUs for prefill and 64 for decode within one scale-up domain, so a smaller setup will not match the charts directly.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "Linux with GCC 13.0 or newer and Python 3.12",
  "NVIDIA SM100 GPU with CUDA 13, or Huawei Ascend 950 NPU with CANN 9.2",
  "Access to the deepseek-ai/DeepSeek-V4.1-Flash-1017 checkpoint on Hugging Face, or a local copy",
  "Enough disk space and memory for the checkpoint and the build"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.7,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/deepseek-ai-deepinfer/benchmark-prefill-and-decode-throughput/",
 "md": "https://dedupedai.com/use-cases/deepseek-ai-deepinfer/benchmark-prefill-and-decode-throughput/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/deepseek-ai-deepinfer--benchmark-prefill-and-decode-throughput.json",
 "api_version": "v1"
}