Jesse Gross 0b9c6cb497 ggml: Export GPU UUIDs ... This enables matching up devices and information reported by the backend with system management libraries such as nvml to get accurate free memory reporting.		2025-12-29 06:38:10 -06:00
..
ggml-blas	Revert "cgo: use O3"	2025-01-31 10:25:39 -08:00
ggml-cpu	chore: disable debug in binary libraries (#10788)	2025-12-29 06:38:04 -06:00
ggml-cuda	ggml: Export GPU UUIDs	2025-12-29 06:38:10 -06:00
ggml-hip	llama: update to commit 2016f07b (#10352)	2025-12-29 06:37:42 -06:00
ggml-metal	ggml: Export GPU UUIDs	2025-12-29 06:38:10 -06:00
CMakeLists.txt	llama: update to commit de4c07f93 (#10655)	2025-12-29 06:37:57 -06:00
ggml-alloc.c	ggml: Report graph memory for failed allocations	2025-12-29 06:38:06 -06:00
ggml-backend-impl.h	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
ggml-backend-reg.cpp	chore: update mllama to use ollama engine (#10637)	2025-12-29 06:37:59 -06:00
ggml-backend.cpp	ggml: Report graph memory for failed allocations	2025-12-29 06:38:06 -06:00
ggml-common.h	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
ggml-impl.h	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
ggml-opt.cpp	llama: update to commit de4c07f93 (#10655)	2025-12-29 06:37:57 -06:00
ggml-quants.c	llama: update to commit de4c07f93 (#10655)	2025-12-29 06:37:57 -06:00
ggml-quants.h	next build (#8539)	2025-01-29 15:03:38 -08:00
ggml-threading.cpp	next build (#8539)	2025-01-29 15:03:38 -08:00
ggml-threading.h	next build (#8539)	2025-01-29 15:03:38 -08:00
ggml.c	chore: update mllama to use ollama engine (#10637)	2025-12-29 06:37:59 -06:00
ggml.go	all: fix cgo compiler warnings on windows (#10563)	2025-12-29 06:37:51 -06:00
ggml_darwin_arm64.go	llama: update llama.cpp vendor code to commit d7cfe1ff (#9356)	2025-02-26 20:34:44 -08:00
gguf.cpp	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
ollama-debug.c	ollama-debug.c: change 'ld' to 'PRIi64'	2025-03-13 17:10:37 +08:00