10-17-2026, 06:10 AM
That matches what I was seeing. The pattern around continuous batching has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
|
Search / Retrieval / Reranking discussion with vLLM
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
Search / Retrieval / Reranking discussion with vLLM - by visionforge - 10-15-2026, 05:53 PM
Re: Search / Retrieval / Reranking discussion with vLLM - by promptspark58 - 10-17-2026, 06:10 AM
Re: Search / Retrieval / Reranking discussion with vLLM - by cacheplane98 - 10-17-2026, 08:42 AM
|