distillation that keeps useful behavior with vLLM

Thread Rating:

0 Vote(s) - 0 Average
1
2
3
4
5

Linear Mode

distillation that keeps useful behavior with vLLM

batchscope72 Offline

Offline

Junior Member

Posts: 39
Threads: 8
Joined: Aug 2026
Reputation: 0

#10

10-14-2026, 02:45 PM

I think the bottleneck is somewhere else. I've seen people blame tokens/sec when the real issue was much more mundane.

mostly local

Find

Reply

« Next Oldest | Next Newest »

Messages In This Thread

distillation that keeps useful behavior with vLLM - by quiettoken - 10-10-2026, 06:53 AM

Re: distillation that keeps useful behavior with vLLM - by plainember52 - 10-11-2026, 06:55 PM

Re: distillation that keeps useful behavior with vLLM - by quietstack - 10-14-2026, 02:12 AM

Re: distillation that keeps useful behavior with vLLM - by vramridge - 10-12-2026, 07:37 AM

Re: distillation that keeps useful behavior with vLLM - by thetagrid15 - 10-12-2026, 07:55 AM

Re: distillation that keeps useful behavior with vLLM - by quietstack - 10-12-2026, 10:20 AM

Re: distillation that keeps useful behavior with vLLM - by turboyard94 - 10-12-2026, 08:55 AM

Re: distillation that keeps useful behavior with vLLM - by amberpatch25 - 10-12-2026, 10:42 AM

Re: distillation that keeps useful behavior with vLLM - by turboyard94 - 10-12-2026, 01:25 PM

Re: distillation that keeps useful behavior with vLLM - by batchscope72 - 10-14-2026, 02:45 PM

Re: distillation that keeps useful behavior with vLLM - by emberpeak - 10-14-2026, 03:39 PM

View a Printable Version

Forum Jump:

Users browsing this thread: 1 Guest(s)