Aller au contenu

Daniele Salatti

@danielesalatti.com did:plc:r2skelzh7excleps23iselts

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

Sur Bluesky depuis le

Abonnés
601
Abonnements
433
Posts
1 232
Jours dans les classements
0

Résumé

Daniele Salatti (@danielesalatti.com) est sur Bluesky depuis le 25 mai 2023. Le compte a 601 abonnés, suit 433 comptes et a publié 1 232 posts.

Présence dans les classements

Les meilleurs jours où les posts de ce compte sont entrés dans le top quotidien de Debya.

Ce compte n’est encore apparu dans aucun classement quotidien.

Posts aimés récemment

J’aime publics du réseau Bluesky.

  • 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!)

    Voir le post
  • 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

    Voir le post
  • 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

    Voir le post
  • 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)

    Voir le post
  • 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.

    Voir le post

Connectez-vous pour en voir plus

Comptes bloqués

Sur Bluesky, les blocages sont publics.