Press Space to continue
Curated tech posts from X on AI, startups, and product development—signal without the doomscroll, updated on weekdays.
Press Space to continue
Press Space to continue
1000 tokens/s or 1ms latency per token! insane but doable with nvfp4 quantization, dflash speculation, warp specialization, and data transfer/compute overlap. you likely also have to keep concurrency low to sustain this given 3x price.
@XiaomiMiMoQuoted post unavailable hereOpen on X