10-07-2026, 06:27 AM
Ran a quick check on my box. On 4090 with vLLM, I saw basically the same behavior. The main thing that moved was latency, not quality.
Inference
›
Training & Customization
›
Fine-Tuning / LoRA
how much orchestration is too much: early impressions
how much orchestration is too much: early impressions
|
how much orchestration is too much: early impressions
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
how much orchestration is too much: early impressions - by llm_wren - 10-04-2026, 08:30 PM
Re: how much orchestration is too much: early impressions - by llm_wren - 10-04-2026, 09:49 PM
Re: how much orchestration is too much: early impressions - by southden - 10-05-2026, 12:33 AM
Re: how much orchestration is too much: early impressions - by quiethouse - 10-06-2026, 01:06 AM
Re: how much orchestration is too much: early impressions - by labline - 10-07-2026, 01:46 AM
Re: how much orchestration is too much: early impressions - by northgrid33 - 10-07-2026, 03:50 AM
Re: how much orchestration is too much: early impressions - by macronest - 10-07-2026, 06:27 AM
|
Users browsing this thread: 1 Guest(s)