註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Aliez Ren
@aliez_ren
套利工具 @taoli_tools 池子区间
加入 June 2014
1.8K 正在關注    18.2K 粉絲
Great work! tested on my 4x RTX Pro 6000 (workstation edition but limit power to 300W each) with PCIe 4.0: tp=2, pp=2: prefill 1570, decode 34 tp=4, pp=1: prefill 967, decode 49 my dockerfile:
顯示更多
GLM-5.1-478B-NVFP4 Running on: - 4x RTX Pro 6000 - Sglang - 370,000 max tokens (1.75x full context) - p10 27.7 | p90 45.6 tok/s decode (gen) - 1340 tok/s prefill I could get 2x decode if I limit to 64k context (100 tok/s) In this video it operates Figma (:
顯示更多