+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: RAG & Knowledge Systems (https://www.datasculpting.ai/inference/forumdisplay.php?fid=14)
+--- Forum: Embeddings (https://www.datasculpting.ai/inference/forumdisplay.php?fid=59)
+--- Thread: Embeddings discussion: early impressions (/showthread.php?tid=1321)
Pages:
1
2
Embeddings discussion: early impressions - ggufwire22 - 10-16-2026
Did a bit of testing and thought I'd post the result here.
I tried this with FLUX using vLLM on GB200. The headline result was better than I expected, but router policy still ended up being the limiting factor.
Curious if anyone else landed in the same place.
Re: Embeddings discussion: early impressions - vectorshed43 - 10-17-2026
Quote:Did a bit of testing and thought I'd post the result here.
Appreciate the detail. That matches what I saw on GB200. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: Embeddings discussion: early impressions - edgecoast - 10-17-2026
Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
Re: Embeddings discussion: early impressions - paperport64 - 10-17-2026
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
Re: Embeddings discussion: early impressions - ggufwire22 - 10-18-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: Embeddings discussion: early impressions - edgecoast - 10-18-2026
I hit almost the same issue last night.
Re: Embeddings discussion: early impressions - vectorshed43 - 10-18-2026
What exact setup are you running? Is this local-only or are you routing anything externally?
Re: Embeddings discussion: early impressions - quantnest - 10-18-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: Embeddings discussion: early impressions - sysstation69 - 10-18-2026
Good point. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: Embeddings discussion: early impressions - mangopath4 - 10-19-2026
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.