Y
Hacker News
new
|
ask
|
show
|
jobs
by
mycelia
151 days ago
Hi! This benchmarking was done w/ DeepSeek-V3's published FP8 weights. And Blackwell performance is still being optimized. SGLang hit 14k/s/B200 though, pretty cool writeup here:
https://lmsys.org/blog/2025-09-25-gb200-part-2/