prefix caching on repeated workflows for Gemma
|
prefix caching on repeated workflows for Gemma
|
10-13-2026, 02:28 PM
Quote:I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tool calling. Once you k A couple questions before I guess too hard. Are you testing this on mini PC or something else?
measure twice, benchmark three times
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
prefix caching on repeated workflows for Gemma - by deepseeked - 10-13-2026, 08:29 AM
Re: prefix caching on repeated workflows for Gemma - by cacheline - 10-13-2026, 12:38 PM
Re: prefix caching on repeated workflows for Gemma - by pixelcrate82 - 10-13-2026, 01:36 PM
Re: prefix caching on repeated workflows for Gemma - by cacheline - 10-14-2026, 02:35 AM
Re: prefix caching on repeated workflows for Gemma - by cacheline - 10-13-2026, 02:28 PM
Re: prefix caching on repeated workflows for Gemma - by modbench - 10-15-2026, 02:47 AM
Re: prefix caching on repeated workflows for Gemma - by cacheline - 10-15-2026, 07:37 AM
|
