Jesse Gross 7b9ab4cb32 ggml: Seperate tensor load from backend creation ...

Currently, when the backend is created, the tensors are loaded at the
same time, which is a slow operation. This separates them to be two
steps:
 - Create backend, including enumerating tensors and memory allocation
 - Loading tensor data

This allows more flexibility in managing model loading.

2025-12-29 06:38:02 -06:00

..

ggml_test.go

default slice values

2025-12-29 06:37:44 -06:00

ggml.go

ggml: Seperate tensor load from backend creation

2025-12-29 06:38:02 -06:00

gguf_test.go

ggml: Seperate tensor load from backend creation

2025-12-29 06:38:02 -06:00

gguf.go

fix data race in WriteGGUF (#10598)

2025-12-29 06:37:53 -06:00

type.go

Follow up to #10363 (#10647)

2025-12-29 06:37:57 -06:00