目录 / ComputeSage StackBench
MCP
鉴权未知
未评级
已上架
ComputeSage StackBench
Search public GPU and LLM benchmark evidence for free, then pay per call for deployment-fit checks, performance predictions, hardware recommendations, and launch configurations.
该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链
接入信息
- 传输形态
- http
- 鉴权方式
- 鉴权未知
- 端点
https://stackbench--computesage.run.tools
鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段
{
"mcpServers": {
"ComputeSage StackBench": {
"url": "https://stackbench--computesage.run.tools"
}
}
}
能力清单
| 工具 | 说明 |
|---|---|
| search_evidence | $0.00 free search of bounded public StackBench benchmark and failure evidence; use this for evidence-only requests. |
| check_deployment_fit | $0.01 USDC on Base mainnet: check model/configuration fit against bounded StackBench capacity evidence. |
| predict_performance | $0.05 USDC: predict configuration throughput, memory, and power from bounded StackBench evidence with confidence, missing metrics, and caveats. |
| recommend_deployment | $0.25 USDC: recommend what to buy or run from bounded StackBench fit, performance, confidence, evidence, caveats, and economics only when supported. |
| generate_launch_config | $0.50 USDC: generate deterministic vLLM or llama.cpp launch templates from an exact StackBench recommendation without claiming a launch occurred. |
纠错与举报（发现条目失效、署名有误或涉及侵权？）
提交举报 / 纠错
侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。