OpenRouterTeam/openrouter-runner

• highreadme#1

  Clarify README to explicitly state archived status and guide to current solutions

  原因：

  当前

  This repo is an artifact from the early days of OpenRouter, when the opensource LLM provider ecosystem was much more nascent. Early adopters wanted to chat with niche fine-tunes, so we built this with vllm to serve them. No longer in use, but preserved here for historical purposes. Check out the current models list here, or head over to our docs to learn more about our modern features for growing startups and enterprises alike.

  复制粘贴的修复

  复制

  This repository is an **archived artifact** from the early days of OpenRouter and is **no longer maintained or intended for active use**. It is preserved here for historical context only. For current OpenRouter features, models, and integration methods, please visit our main site at [https://openrouter.ai](https://openrouter.ai) and our documentation.

  待办完成忽略
• hightopics#2

  Add relevant topics to the repository

  原因：

  复制粘贴的修复

  复制

  ["deprecated", "archive", "llm-inference", "openrouter", "vllm", "historical"]

  待办完成忽略
• mediumabout#3

  Update the repository description to reflect its archived status

  原因：

  当前

  Deprecated inference engine

  复制粘贴的修复

  复制

  Archived: Historical OpenRouter inference engine (vLLM-based), no longer maintained or for active use.

  待办完成忽略

本次扫描解析到的品类 GEO 通道：google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• 品类问题

  How to run custom large language models for specialized applications?

  你：未被推荐
  AI 推荐顺序：

  1. Hugging Face Transformers (huggingface/transformers)
  2. Accelerate (huggingface/accelerate)
  3. vLLM (vllm-project/vllm)
  4. NVIDIA Triton Inference Server (triton-inference-server/server)
  5. OpenVINO (openvinotoolkit/openvino)
  6. ONNX Runtime (microsoft/onnxruntime)
  7. MLflow (mlflow/mlflow)
  8. Ray Serve (ray-project/ray)

  AI 推荐了 8 个替代方案，却始终没点名 OpenRouterTeam/openrouter-runner。这就是要补上的差距。

  查看 AI 完整回答
• 品类问题

  What are efficient inference engines for serving custom LLMs with high throughput?

  你：未被推荐
  AI 推荐顺序：

  1. vLLM
  2. NVIDIA TensorRT-LLM
  3. DeepSpeed-MII
  4. TGI (Text Generation Inference)
  5. OpenVINO
  6. ONNX Runtime
  7. TorchServe

  AI 推荐了 7 个替代方案，却始终没点名 OpenRouterTeam/openrouter-runner。这就是要补上的差距。

  查看 AI 完整回答

• Metadata completeness

  warn

  建议：

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of OpenRouterTeam/openrouter-runner?

  pass
  ✓AI 明确点名了 OpenRouterTeam/openrouter-runner

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• If a team adopts OpenRouterTeam/openrouter-runner in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI 明确点名了 OpenRouterTeam/openrouter-runner

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• In one sentence, what problem does the repo OpenRouterTeam/openrouter-runner solve, and who is the primary audience?

  pass
  ✓AI 明确点名了 OpenRouterTeam/openrouter-runner

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？