Vector Databases discussion for DeepSeek

[southspark]

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?

Simple and boring is a valid answer.

[southspark]

worth checking the driver first.

[tinycontext]

worth checking the driver first.

I tested this tonight. On Threadripper box with TensorRT-LLM, I saw basically the same behavior. The main thing that moved was latency, not quality.

[southspark]

Good point. That matches what I saw on mini PC.

[fastfield4]

Ran a quick check on my box. 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.

[orbitbench6]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tokens/sec. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.