Jesse Gross d773b7d671 backend: API to support full precision matmul ... Most tensor backends try to optimize performance by using a lower precision for matmuls. However, some operations (such as kq) on some models are sensitive to this and require full precision.		2025-02-13 17:09:26 -08:00
..
imageproc.go	imageproc mllama refactor (#7537)	2024-12-14 19:50:15 -08:00
imageproc_test.go	imageproc mllama refactor (#7537)	2024-12-14 19:50:15 -08:00
model.go	next ollama runner (#7913)	2025-02-13 16:31:21 -08:00
model_text.go	backend: API to support full precision matmul	2025-02-13 17:09:26 -08:00
model_vision.go	backend: Consistently use int (vs. int64) for tensor shapes	2025-02-13 17:09:26 -08:00
process_image.go	next ollama runner (#7913)	2025-02-13 16:31:21 -08:00