+- 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 GB200 (/showthread.php?tid=1073)
Pages:
1
2
Re: MCP server discovery mess on GB200 - promptpoint - 10-12-2026
worth checking the driver first.
Re: MCP server discovery mess on GB200 - northquill - 10-13-2026
Quote:worth checking the driver first.
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at batch size. Not glamorous advice, but repeatable baselines save a lot of time. Turns out 'just one more test' was a lie.
Re: MCP server discovery mess on GB200 - vramarch - 10-14-2026
That matches what I was seeing. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: MCP server discovery mess on GB200 - tensorkite - 10-14-2026
Interesting, I hadn't tried that. I don't think your conclusion is far off.
Re: MCP server discovery mess on GB200 - macrostack69 - 10-17-2026
Appreciate the detail. I ended up in about the same place using MLX. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: MCP server discovery mess on GB200 - flintriver50 - 10-18-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there.