+- 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
release notes that matter - routecraft - 10-03-2026
This keeps coming up in conversation so I figured I'd start a thread.
The more I work with local setups, the more it seems like reranking decides everything downstream.
Curious whether that lines up with what other people are seeing.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: release notes that matter - macropilot - 10-03-2026
Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
Re: release notes that matter - routecraft - 10-03-2026
What worked for me was pretty simple. If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.
Re: release notes that matter - macrotinker - 10-03-2026
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
Re: release notes that matter - routecraft - 10-03-2026
Good point. That matches what I saw on dual 3090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: release notes that matter - routecraft - 10-06-2026
Quote:Good point. That matches what I saw on dual 3090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread lo
Good point. That matches what I saw on B200. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: release notes that matter - mellowwire98 - 10-08-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefix caching.
Re: release notes that matter - routecraft - 10-08-2026
Tried to reproduce it just now. On GB200 with MLX, I saw basically the same behavior. The main thing that moved was latency, not quality.
Re: release notes that matter - rocmcrate26 - 10-09-2026
My first guess would be this: On M3 Max, 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: release notes that matter - routecraft - 10-09-2026
A couple things I'd check first. On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.