註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Leroy Li
@LeroyLi311063
Just my thoughts
加入 July 2025
33 正在關注    888 粉絲
Deployment of DeepSeek-V4.1-Flash using FP8-FP4 mixed on 32 Ascend 950DT. For 128K sequence scenarios, single-card decoding throughput reaches 5,800 TPS at 13.79 ms. In low-latency inference scenarios, latency is kept under 5 ms while achieving a throughput of 2,727.
顯示更多