[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / r / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
▼ Settings Mobile Home
/g/ - Technology
Return Catalog Bottom Refresh
Thread archived.
You cannot reply anymore.
[Advertise on 4chan]
[Return] [Catalog] [Bottom]
Anonymous Archived
 No.108798052
 No.108798052 Archived
>$CURRENT_DATE
>I am forgotten
name a biggest nothing burger for current year
2 months in and still no non buggy piece of shit implementation aside from internal google datacenters
memory stock and ram prices has completely rebounded and more
>>
Anonymous
 No.108798066
 No.108798066
turbo quant sounds like something you call a sped in high school
>>
Anonymous
 No.108798109
 No.108798109
>>108798066
>australian guy describing a terrific woman
>>
Anonymous
 No.108798120
 No.108798120
>>108798052
it just wasnt the win we wanted it to be. it only lowers context memory usage, the entire model still needs to fit inside memory.
>>
Anonymous
 No.108798641
 No.108798641
>>108798120
just being able to fit full context within the very last gbs, without all the massive compromises involved would have been a huge win
>>
Anonymous
 No.108799403
 No.108799403
>>108798052
well, the real issue is that in real world testing turboquant falls below performance of the existing kv quant techniques. it was a complete nothingburger.
[Return] [Catalog] [Top]
Post a Reply
Return Catalog Top Refresh
[Advertise on 4chan]
Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.