Georgi Gerganov d6e7b033a4 llama : add option to save memory in device buffers (#22679) ...

* llama : add option to save memory in device buffers

* tests : extend llama-save-load-state

2026-05-05 06:35:07 +03:00

..

CMakeLists.txt

docs : Minor cleanups (#19252)

2026-02-02 08:38:55 +02:00

ggml-metal-common.cpp

models : optimize qwen3next graph (#19375)

2026-02-14 12:57:36 +02:00

ggml-metal-common.h

metal : refactor + optimize v2 (#15995)

2025-09-17 20:38:12 +03:00

ggml-metal-context.h

metal : support virtual devices (#18919)

2026-02-02 14:29:44 +02:00

ggml-metal-context.m

metal : avoid divisions in bin kernel (#20426)

2026-03-12 09:42:40 +02:00

ggml-metal-device.cpp

metal : optimize Metal Tensor API usage for GGML_OP_MUL_MAT (#20962)

2026-04-25 15:14:28 +03:00

ggml-metal-device.h

llama : add option to save memory in device buffers (#22679)

2026-05-05 06:35:07 +03:00

ggml-metal-device.m

llama : add option to save memory in device buffers (#22679)

2026-05-05 06:35:07 +03:00

ggml-metal-impl.h

metal : optimize Metal Tensor API usage for GGML_OP_MUL_MAT (#20962)

2026-04-25 15:14:28 +03:00

ggml-metal-ops.cpp

metal : optimize Metal Tensor API usage for GGML_OP_MUL_MAT (#20962)

2026-04-25 15:14:28 +03:00

ggml-metal-ops.h

metal: Implement ROLL op (#21946)

2026-04-16 11:54:37 +03:00

ggml-metal.cpp

llama : add option to save memory in device buffers (#22679)

2026-05-05 06:35:07 +03:00

ggml-metal.metal

metal : optimize Metal Tensor API usage for GGML_OP_MUL_MAT (#20962)

2026-04-25 15:14:28 +03:00