Aman Gupta 57291f2644 ggml: allow passing alloc dependencies in graph_optimize (#27301) ...

* ggml: allow passing alloc dependencies in graph_optimize

* add alloc dep tests

* add TODO about using flat array

2026-08-30 11:34:20 +08:00

..

backend

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

include

ggml-virtgpu: improve the reliability of the code (#19846)

2026-02-26 20:00:57 +08:00

apir_cs_ggml-rpc-front.cpp

ggml-virtgpu: make the code thread safe (#19204)

2026-02-04 10:46:18 +08:00

CMakeLists.txt

…

ggml-backend-buffer-type.cpp

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

ggml-backend-buffer.cpp

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

2026-04-09 16:42:19 +02:00

ggml-backend-device.cpp

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

ggml-backend-reg.cpp

ggml-virtgpu: improve the reliability of the code (#19846)

2026-02-26 20:00:57 +08:00

ggml-backend.cpp

ggml: allow passing alloc dependencies in graph_optimize (#27301)

2026-08-30 11:34:20 +08:00

ggml-remoting.h

ggml-virtgpu: improve the reliability of the code (#19846)

2026-02-26 20:00:57 +08:00

ggmlremoting_functions.yaml

ggml-virtgpu: make the code thread safe (#19204)

2026-02-04 10:46:18 +08:00

regenerate_remoting.py

ggml-virtgpu: improve the reliability of the code (#19846)

2026-02-26 20:00:57 +08:00

virtgpu-apir.h

…

virtgpu-forward-backend.cpp

ggml-virtgpu: improve the reliability of the code (#19846)

2026-02-26 20:00:57 +08:00

virtgpu-forward-buffer-type.cpp

ggml-virtgpu: improve the reliability of the code (#19846)

2026-02-26 20:00:57 +08:00

virtgpu-forward-buffer.cpp

ggml-virtgpu: improve the reliability of the code (#19846)

2026-02-26 20:00:57 +08:00

virtgpu-forward-device.cpp

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

virtgpu-forward-impl.h

ggml-virtgpu: improve the reliability of the code (#19846)

2026-02-26 20:00:57 +08:00

virtgpu-forward.gen.h

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

virtgpu-shm.cpp

ggml-virtgpu: fix circular dependency in headers (#22557)

2026-05-02 21:28:50 +08:00

virtgpu-shm.h

…

virtgpu-utils.cpp

…

virtgpu-utils.h

…

virtgpu.cpp

ggml-virtgpu: fix circular dependency in headers (#22557)

2026-05-02 21:28:50 +08:00

virtgpu.h

ggml-virtgpu: fix circular dependency in headers (#22557)

2026-05-02 21:28:50 +08:00