Hi DeepSeek Team, thanks for the great work on DeepSeek-V3 and the detailed deployment profile.
I have a clarification question regarding PD (Prefill–Decode) separation during deployment.
When you mention the decoding batch size, does this refer to:
- The number of active sequences being decoded concurrently in the system (i.e., batch size at the sequence/request level), or
- The number of tokens processed by experts in the decoding stage (i.e., token-level batching inside the MoE/expert execution)?
Understanding this distinction would be very helpful for correctly interpreting the performance analysis and for reproducing similar deployment settings.
Hi DeepSeek Team, thanks for the great work on DeepSeek-V3 and the detailed deployment profile.
I have a clarification question regarding PD (Prefill–Decode) separation during deployment.
When you mention the decoding batch size, does this refer to:
Understanding this distinction would be very helpful for correctly interpreting the performance analysis and for reproducing similar deployment settings.