Georgi Gerganov aa7ee0ba59 ggml : add get_alloc_size_n to buffer type interface ...

- Add ggml_backend_buft_get_alloc_size_n public API
- Add optional get_alloc_size_n callback to ggml_backend_buffer_type_i
- Share tensor->buffer planning between alloc_buffer_n default and get_alloc_size_n default
- Replace unchecked realloc with std::vector in alloc_buffer_n default
- Make ggml_backend_alloc_ctx_tensors_from_buft_size use the new API
- Add test-alloc coverage for get_alloc_size_n

Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp

2026-09-24 17:02:07 +03:00

..

cmake

CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079)

2026-09-09 12:50:08 +02:00

include

ggml : add get_alloc_size_n to buffer type interface

2026-09-24 17:02:07 +03:00

src

ggml : add get_alloc_size_n to buffer type interface

2026-09-24 17:02:07 +03:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

ggml : bump version to 0.25.1 (ggml/1637)

2026-09-23 20:29:29 +03:00