+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Harnesses, Agents & Orchestration (https://www.datasculpting.ai/inference/forumdisplay.php?fid=11)
+--- Forum: Workflows / Automation (https://www.datasculpting.ai/inference/forumdisplay.php?fid=47)
+--- Thread: release notes that matter (/showthread.php?tid=677)
Pages:
1
2
Re: release notes that matter - southden - 10-09-2026
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
Re: release notes that matter - routecraft - 10-10-2026
Quote:Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up befo
Thanks, that helps. That matches what I saw on A6000. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: release notes that matter - routecraft - 10-11-2026
Quote:[quote]Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed
Thanks, that helps. I ended up in about the same place using vLLM. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: release notes that matter - oxidestream - 10-11-2026
that fixed it for me too.
Re: release notes that matter - routecraft - 10-11-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it. Turns out 'just one more test' was a lie.
Re: release notes that matter - routecraft - 10-11-2026
What exact setup are you running? What model, what runtime, and roughly what context size?