+- 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: Help with Embeddings: what are you seeing? (/showthread.php?tid=685)
Help with Embeddings: what are you seeing? - thetanest - 10-03-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of TensorRT-LLM and Threadripper box felt surprisingly usable once I tuned around consumer GPUs.
If someone wants the exact settings I can clean them up and post them.
Re: Help with Embeddings: what are you seeing? - ggufwire22 - 10-03-2026
Quote:Thought I'd post a small recipe because a lot of threads ask similar things.
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tool calling. Once you know the plain path works, then add the faster path back in piece by piece.
Re: Help with Embeddings: what are you seeing? - fusedhall - 10-03-2026
Appreciate the detail. I ended up in about the same place using PyTorch. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: Help with Embeddings: what are you seeing? - edgecoast - 10-03-2026
Maybe, but I had the opposite result. 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: Help with Embeddings: what are you seeing? - labline - 10-04-2026
Quote:Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Coul
Good point. The pattern around INT4 has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: Help with Embeddings: what are you seeing? - vramscope - 10-04-2026
I'd approach it in a boring order. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: Help with Embeddings: what are you seeing? - dockriver - 10-05-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at VRAM headroom. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: Help with Embeddings: what are you seeing? - vectorshed43 - 10-08-2026
Quote:I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at VRAM headroom. A lot of
subscribed, curious where this lands.
Re: Help with Embeddings: what are you seeing? - ggufwire22 - 10-09-2026
Appreciate the detail. I ended up in about the same place using PyTorch. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.