implementation detail · not yet filed
efficient clustering in the embedder
- 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.
For our E2B and E4B edge models, where the final logit calculation becomes a big bottleneck, we even implemented an efficient clustering technique in the embedder to further accelerate generation.
usedinference servingin Gemma 4 MTP draftersGoogle