llama/patches/0001-ggml-backend-malloc-and-free-using-the-same-compiler.patch · 369de832cdca7680c8f50ba196d39172a895fcad · OpenDAS / ollama

ggml: Free ggml_backend_buffer_t when releasing buffer · ccb7eb81

Jesse Gross authored Apr 14, 2025

When ggml_backend_buffer_free() is called, the device memory
is released but not all backends consistently release the actual
ggml_backend_buffer_t in system RAM, causing a memory leak.

Bug #10040

ccb7eb81

0001-ggml-backend-malloc-and-free-using-the-same-compiler.patch 9.01 KB

Replace 0001-ggml-backend-malloc-and-free-using-the-same-compiler.patch