Jesse Gross 756c78cfc7 ggml: Support closing backends ...

In order to iteratively find the best memory allocation, we need to
be able to free backend memory so we can try again.

2025-08-08 14:57:13 -07:00

..

cache_test.go

ollamarunner: Separate text and multimodal graphs

2025-05-15 13:46:20 -07:00

cache.go

ggml: Support closing backends

2025-08-08 14:57:13 -07:00

multimodal.go

ml: Panic rather than return error on tensor allocation failure

2025-05-22 14:38:09 -07:00

runner.go

ggml: Support closing backends

2025-08-08 14:57:13 -07:00