+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: LLM Models (https://www.datasculpting.ai/inference/forumdisplay.php?fid=12)
+--- Forum: Embedding / Reranking Models (https://www.datasculpting.ai/inference/forumdisplay.php?fid=53)
+--- Thread: MCP server discovery mess on B200 (/showthread.php?tid=886)
Pages:
1
2
Re: MCP server discovery mess on B200 - turboyard94 - 10-16-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: MCP server discovery mess on B200 - modrunner27 - 10-18-2026
subscribed, curious where this lands.
Re: MCP server discovery mess on B200 - cozykite - 10-18-2026
Quote:subscribed, curious where this lands.
That matches what I was seeing. I ended up in about the same place using LM Studio. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: MCP server discovery mess on B200 - localpatch78 - 10-18-2026
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.
Re: MCP server discovery mess on B200 - tinycontext - 10-18-2026
Quote:Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to
Need a little more detail here. What model, what runtime, and roughly what context size?