Throughputmaxxing: DeepSeek-V4-Flash on Isambard-AI
Single-node serving throughput for DeepSeek-V4-Flash: baseline, MLA/DP-attention, and MoE kernel choice.
评论
?
参与讨论
Single-node serving throughput for DeepSeek-V4-Flash: baseline, MLA/DP-attention, and MoE kernel choice.