Jesse Gross 9679f40146 ml: Allow models to constrain inputs to a single batch ... Models may require that a set of inputs all be processed as part of the same batch. For example, if an image has multiple patches with fully connected attention between them, we should not split the batch in the middle of an image. Fixes #9697		2025-03-14 15:38:54 -07:00
..
gemma2	Fix tests and drift from main	2025-03-11 14:49:18 -07:00
gemma3	ml: Allow models to constrain inputs to a single batch	2025-03-14 15:38:54 -07:00
llama	gemma2 impl	2025-03-11 14:35:08 -07:00
mllama	fix: error if image requested without vision model	2025-03-13 10:52:09 -07:00
pixtral	models: Move model into their own directory	2025-02-13 17:09:26 -08:00
qwen2vl	models: Move model into their own directory	2025-02-13 17:09:26 -08:00
models.go	gemma2 impl	2025-03-11 14:35:08 -07:00