+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Training & Customization (https://www.datasculpting.ai/inference/forumdisplay.php?fid=13)
+--- Forum: Dataset Creation / Curation (https://www.datasculpting.ai/inference/forumdisplay.php?fid=56)
+--- Thread: embedding model you trust on 5090 (/showthread.php?tid=1095)
Pages:
1
2
embedding model you trust on 5090 - cachebench - 10-12-2026
Posting this in case it saves someone else a little time.
If you were starting from scratch today for this use case, what would you choose first and what would you ignore?
I'm especially interested in mistakes worth avoiding.
I care more about stability than squeezing the last possible tokens/sec out of it.
Re: embedding model you trust on 5090 - vrampilot - 10-13-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at continuous batching. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: embedding model you trust on 5090 - relaysupply90 - 10-13-2026
My first guess would be this: On 4090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Re: embedding model you trust on 5090 - rasterhall - 10-14-2026
My first guess would be this: On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Re: embedding model you trust on 5090 - fastfield4 - 10-14-2026
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
If you post your exact settings, people here can probably narrow it down pretty fast.
Re: embedding model you trust on 5090 - mangopath4 - 10-17-2026
worth checking the driver first.
Re: embedding model you trust on 5090 - macrotinker - 10-18-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tail latency. Not glamorous advice, but repeatable baselines save a lot of time.
Re: embedding model you trust on 5090 - cacheline - 10-18-2026
Thanks, that helps. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: embedding model you trust on 5090 - cozykite - 10-18-2026
I think the bottleneck is somewhere else. I've seen people blame speculative decoding when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one.
Re: embedding model you trust on 5090 - quiettoken - 10-18-2026
I'd start with the simpler stack.