Daniele Salatti

@danielesalatti.com did:plc:r2skelzh7excleps23iselts

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

Bei Bluesky seit 25 Mai 2023

Follower: 601
Folgt: 433
Posts: 1.232
Tage in Ranglisten: 0

Zusammenfassung

Daniele Salatti (@danielesalatti.com) ist seit 25 Mai 2023 auf Bluesky. Das Konto hat 601 Follower, folgt 433 Konten und hat 1.232 Posts veröffentlicht.

Ranglisten-Platzierungen

Die besten Tage, an denen Posts dieses Kontos in Debyas Tagesliste kamen.

Dieses Konto war noch in keiner Tagesrangliste.

Zuletzt gelikte Posts

Öffentliche Likes aus dem Bluesky-Netzwerk.

jake@yetanotheruseless.com28.10.2026 21:46
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!)
Post anzeigen
mr. TIM@timkellogg.me23.10.2026 16:32
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
Post anzeigen
mr. TIM@timkellogg.me23.10.2026 16:32
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
Post anzeigen
brennan@brennan.computer23.10.2026 16:24
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)
Post anzeigen
antirez@antirez.bsky.social20.10.2026 18:50
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.
Post anzeigen