Model techniques map
Techniquesinference & servinginference quantization

ambiguous · filed under inference & serving

Embedding and KV-cache quantization

Focuses compression on the vocabulary embeddings and the model’s short-term-memory cache.

Also called Embedding and KV cache optimization.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

We focused compression on the model’s vocabulary list and its short-term memory.

usedoptimizationin Gemma 4 E2B and E4B edge modelsGoogle

Filed alongside

Other methods under inference & serving :: inference quantization.