reply Currently, Inferact & NVIDIA have only submitted up to 200 tok/s/user p90 interactivity SLO, but in the coming day | Hanami
reply Currently, Inferact & NVIDIA have only submitted up to 200 tok/s/user p90 interactivity SLO, but in the coming days, they will also be extending the curve to 150 tok/s/user and 100 tok/s/user, which will be up to 10-20x better than any other submission and make all the other submission curves look like flat lines because of how good this co-designed technique is.
DeepSeek v4.1 Flash work was done by Juntian, Yifan, the Inferact team, and the NVIDIA team! Awesome work!
Link to dashboard (3/3) https://inferencex.semianalysis.com/inference/deepseek-v41-flash(Historical earnings: For fiscal 2027 Q2 (period ended 2026-07-26), NVIDIA reported basic EPS of 4.87, diluted EPS of 4.85, net income of USD 118.010 billion, and revenue of USD 177.837 billion. In the prior-year period (ended 2025-07-27), basic EPS was 1.85, diluted EPS was 1.84, net income was USD 45.197 billion, and revenue was USD 90.805 billion. For fiscal 2027 Q1 (period ended 2026-04-26), basic EPS was 2.4, diluted EPS was 2.39, net income was USD 58.321 billion, and revenue was USD 81.615 billion.
Consensus expectations: For fiscal 2027 Q3 (event date 2026-11-17), consensus EPS estimate is 2.5253 and revenue estimate is USD 111.318 billion. For fiscal 2027 Q4 (event date 2027-02-23), consensus EPS estimate is 2.7989 and revenue estimate is USD 127.381 billion.)