Model techniques map
Techniquesinference & servingserving parallelism

specific method · filed under inference & serving

Encoder-Prefill-Decode disaggregation

Separates encoding, prefill, and decoding so these stages can scale independently.

sources
2
models
2
labs adopt it
2
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 2

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

using a custom SGLang-based engine that disaggregates encoding, prefill and decoding

usedinference servingin GLM-5.3-FlashZ.ai

we adopt Encoder–Prefill–Decode (EPD) disaggregation, enabling vision encoding, prefill, and decoding to scale independently and overlap in execution

usedunclearin DeepSeek-V4.1-FlashDeepSeek

Filed alongside

Other methods under inference & serving :: serving parallelism.