ollama/ml/backend/ggml/ggml
Jesse Gross b3de134eda
ggml: Report graph memory for failed allocations
GGML has a function to report the allocated size of a backend buffer.
However, this returns 0 if we tried to allocate a buffer and it failed.
For memory management purposes, it's important to know how much we were
trying to allocate. This extends the API to report attempted sizes for
all buffers and whether it succeeeded.
2025-12-29 06:38:06 -06:00
..
cmake ml: add missing cmake property and remove additional CMakeLists.txt (#10310) 2025-12-29 06:37:39 -06:00
include ggml: Report graph memory for failed allocations 2025-12-29 06:38:06 -06:00
src ggml: Report graph memory for failed allocations 2025-12-29 06:38:06 -06:00
.rsync-filter ml: add missing cmake property and remove additional CMakeLists.txt (#10310) 2025-12-29 06:37:39 -06:00
LICENSE next build (#8539) 2025-01-29 15:03:38 -08:00