10-07-2026, 09:53 PM
That matches what I was seeing. I ended up in about the same place using TensorRT-LLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
|
router in front of vLLM: anyone testing this?
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
router in front of vLLM: anyone testing this? - by batchcraft - 10-06-2026, 09:36 AM
Re: router in front of vLLM: anyone testing this? - by turboarch95 - 10-07-2026, 09:53 PM
|
Users browsing this thread: 1 Guest(s)