10-11-2026, 02:14 AM
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.
learning in public
|
70B still worth the pain: worth it?
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
70B still worth the pain: worth it? - by fastbench - 10-11-2026, 01:51 AM
Re: 70B still worth the pain: worth it? - by torchsupply99 - 10-11-2026, 02:14 AM
Re: 70B still worth the pain: worth it? - by vrampilot - 10-11-2026, 02:57 AM
|