Jesse Gross bcd5507f4b 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.		2025-12-29 06:39:51 -06:00
..
cache.go	ggml: Support closing backends	2025-12-29 06:39:51 -06:00
cache_test.go	ollamarunner: Separate text and multimodal graphs	2025-12-29 06:38:01 -06:00
multimodal.go	ml: Panic rather than return error on tensor allocation failure	2025-12-29 06:38:06 -06:00
runner.go	ggml: Support closing backends	2025-12-29 06:39:51 -06:00