{
 "schema_version": 1,
 "generated": "2026-10-24",
 "repo": "deepseek-ai/DeepInfer",
 "name": "DeepInfer",
 "owner": "deepseek-ai",
 "slug": "deepseek-ai-deepinfer",
 "github": "https://github.com/deepseek-ai/DeepInfer",
 "what": "DeepInfer is an open-source, high-performance offline inference framework from DeepSeek for running DeepSeek models, currently DeepSeek-V4.1-Flash, on NVIDIA SM100 GPUs or Huawei Ascend 950 NPUs.",
 "why": "19k stars, launched 6 days ago, talked about in 5 AI sources we track",
 "language": "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"
 ],
 "audience_note": "Written for ML engineers and infrastructure teams with SM100 GPU or Ascend 950 NPU access who want to run or benchmark DeepSeek models locally.",
 "risk": "none",
 "section": "weekly",
 "weekly_rank": 1,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/deepseek-ai-deepinfer/",
 "use_case_count": 4,
 "use_cases": [
  {
   "id": "deepseek-ai-deepinfer--run-offline-inference-deepseek-v4-flash",
   "title": "Run offline inference on DeepSeek-V4.1-Flash locally",
   "best": true,
   "url": "https://dedupedai.com/use-cases/deepseek-ai-deepinfer/run-offline-inference-deepseek-v4-flash/",
   "json": "https://dedupedai.com/use-cases/u/deepseek-ai-deepinfer/run-offline-inference-deepseek-v4-flash.json"
  },
  {
   "id": "deepseek-ai-deepinfer--get-repeatable-outputs-with-deterministic-sampling",
   "title": "Get repeatable model outputs for regression tests",
   "best": false,
   "url": "https://dedupedai.com/use-cases/deepseek-ai-deepinfer/get-repeatable-outputs-with-deterministic-sampling/",
   "json": "https://dedupedai.com/use-cases/u/deepseek-ai-deepinfer/get-repeatable-outputs-with-deterministic-sampling.json"
  },
  {
   "id": "deepseek-ai-deepinfer--constrain-model-output-to-json-schema",
   "title": "Force model output to match a JSON schema",
   "best": false,
   "url": "https://dedupedai.com/use-cases/deepseek-ai-deepinfer/constrain-model-output-to-json-schema/",
   "json": "https://dedupedai.com/use-cases/u/deepseek-ai-deepinfer/constrain-model-output-to-json-schema.json"
  },
  {
   "id": "deepseek-ai-deepinfer--benchmark-prefill-and-decode-throughput",
   "title": "Reproduce Deep Infer prefill and decode benchmarks",
   "best": false,
   "url": "https://dedupedai.com/use-cases/deepseek-ai-deepinfer/benchmark-prefill-and-decode-throughput/",
   "json": "https://dedupedai.com/use-cases/u/deepseek-ai-deepinfer/benchmark-prefill-and-decode-throughput.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}