Michael Yang 0796d79d19 cuda: skip large batches ...

cuda panics on batches larger than 1024 so skip those and fallback to
cpu

2025-11-18 16:11:37 -08:00

..

backend

cuda: skip large batches

2025-11-18 16:11:37 -08:00

nn

Add deepseek v3.1 (#13063)

2025-11-17 18:03:21 -08:00

backend.go

deepseekocr

2025-11-18 16:11:37 -08:00

device.go

llm: Prefer dedicated GPUs over iGPUs when allocating memory

2025-11-11 13:11:08 -08:00

path.go

cpu: always ensure LibOllamaPath included (#12890)

2025-10-31 14:37:29 -07:00