Unverified50% confidenceSolutionExact time
DeepSeek separates the pre-fill and decode phases onto different machines: pre-fill runs on regular eight-GPU machines, while decode runs on a supernode composed of hundreds of GPUs.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDeepSeek adopts a PD-separated architecture, deploying the Pre-fill stage and the Decode stage on different machines: an 8-card server for reading the question and a 64-to-128-card supernode for writing the answer.77% similarUnverifiedThe production solution introduced by DeepSeek deploys visual encoding, prefill and decode separately, each with its own machines, so they can scale independently for different resource bottlenecks.73% similarUnverifiedIn the decode phase, DeepSeek spreads MoE experts across more than 64 GPUs, with each GPU holding only a small number of experts.73% similarUnverifiedThe new DeepSeek model adopts an encoder-decoder hybrid architecture, splitting the 40-layer network in the middle, with the bottom 20 layers serving as the encoder and the top 20 layers as the decoder.69% similarUnverifiedDeepSeek-Coder-V2-Lite is a programming-specific model that can run on 8 GB of VRAM after quantization.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1082052API
curl https://kongchang.com/api/v1/knowledge/claims/1082052MCP
get_claim(id=1082052)