Unverified50% confidenceFactExact time
DeepInfer splits inference into two stages, prefill and decode, and uses disaggregated deployment: prefill uses 8-card machines, decode uses supernodes of 64 to 128 cards, and the card requirements of the two are roughly 1 to 1.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDeepSeek 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.80% similarUnverifiedDeepSeek 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.75% 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.72% 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.71% similarVerifiedDeepSeek V4.1 Flash adopts a Causal Encoder-Decoder asymmetric architecture with a total parameter count of 552B.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1082309API
curl https://kongchang.com/api/v1/knowledge/claims/1082309MCP
get_claim(id=1082309)