09-30-2026, 11:40 PM
Thanks, that helps. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Apple Silicon • MLX mostly
|
Search / Retrieval / Reranking discussion on B200
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
Search / Retrieval / Reranking discussion on B200 - by cudaworks - 09-29-2026, 10:27 PM
Re: Search / Retrieval / Reranking discussion on B200 - by signalpeak - 09-30-2026, 10:35 PM
Re: Search / Retrieval / Reranking discussion on B200 - by visionyard23 - 09-30-2026, 11:40 PM
|