Charles Frye Prepares Slides On Production Inference Lessons For Transformers Talk
No Digg Deeper questions have been answered for this story yet.
Most Activity
thrilled to discuss Rollouts of Transformers, with a special appearance at the end of "Bots" that are "Auto"
the talk will be available live and on YouTube!
Stanford CS25 Talk TOMORROW (Thurs, 5/28) at 4:30pm PST 🤖
Charles Frye (@charles_irl) from @modal on: Serving Transformers: Lessons from the trenches of production inference
Training models is only half the battle. Actually serving them at scale is where things get real 👇 (1/6)

@kernel_trick @samlakig for this one, at least, you don't have to be <3

@charles_irl ngl wish i was at stanford fr

@samlakig @charles_irl yeah...

@charles_irl got any remote internships 🥺

@charles_irl Ya’ll do influencer partnerships 🤔?
Asking cause I run a C++ deep-dive YT channel with ~30k subs and ~150k monthly views.

@charles_irl @kernel_trick 🫡🫡🫡