Mike Ravkine PRO
mike-ravkine
AI & ML interests
LLM Research / Development / Evaluation
Recent Activity
posted
an
update
1 day ago
How many 3090 is too many 3090? Trick question - never enough 🤖.
Working on rewiring for a 5th this weekend so need the quad in 4U to make this happen. Definitely pushing air cooling to its limit but NVLink requires aggressive spacing between the cards.
Fortunately up here in Canada our power is quite cheap, so stacking compute this way works. While being annoying in terms of physical constraint the NVlink bridges really helps squeeze these cards - on smaller models at big batch the difference at -tp 2 can be as much as 50%. It's not bandwidth, it's latency!
upvoted
a
paper
2 days ago
The End of Manual Decoding: Towards Truly End-to-End Language Models
Organizations
None yet