İçeriğe geç
debya
Türkçe
Giriş yap Ücretsiz üye ol
Bluesky’da aç Bu hesabı takip et

Daniele Salatti

@danielesalatti.com did:plc:r2skelzh7excleps23iselts

Here’s to now! LLMs, AI, Software Engineering, Mountaineering, Sailing Seattle, USA ↔ Livorno, Italy danielesalatti.it

Bluesky’a katılma tarihi:

Takipçi
601
Takip edilen
433
Post
1.232
Sıralamaya girdiği gün
0

Özet

Daniele Salatti (@danielesalatti.com), 25 Mayıs 2023 tarihinde katılan bir Bluesky kullanıcısı. 601 takipçisi var, 433 hesabı takip ediyor ve 1.232 post paylaştı.

Sıralama geçmişi

Bu hesabın postlarının Debya günlük listesine girdiği en iyi günler.

Bu hesap henüz günlük sıralamaya girmedi.

Son beğendiği postlar

Bluesky ağındaki herkese açık beğeniler.

  • jake@yetanotheruseless.com

    I do not have that problem, as I split across Ant/OAI/GOOG/some long tail of OpenRouter GLM/DS models to keep making sure I know how well they do. (my problem, instead, is spending giant gob-tons on tokens!)

    Postu göster
  • mr. TIM@timkellogg.me

    memory bandwidth is the typical constraint LLMs are so large that the they have to be paged close to the compute cores. When you batch, you can process several requests in one single matrix multiply operation so you spend less time moving weights around, more doing actual computations

    Postu göster
  • mr. TIM@timkellogg.me

    imo speculative decoding is such a huge win for local LLMs keeping a GPU busy basically boils down to batching, but on a laptop you don’t have multiple users whereas SD allows you to batch across sequential tokens (basically) which lets you maximize the value you’re getting out of your GPU

    Postu göster
  • brennan@brennan.computer

    I've owned and assembled a heck of a lot of it, it's a marvel of design and manufacturing and logistics as I get older their solid wood options are often nice, I'm just sort of phasing out of my cardboard era their apartment sizing schtick is now too small as I moved out of my apartment(s)

    Postu göster
  • antirez@antirez.bsky.social

    DeepSeek infer is the cloud version of DwarfStar, conceptually. Vertical inference engine for one model and specific hardware. Good move. And well, a lesson to the ones that criticized this approach as well.

    Postu göster

Daha fazlası için üye girişi yap

Blokladığı hesaplar

Bluesky’da bloklar herkese açık kayıtlardır.