llama.cpp/ggml
Radoslav Gerganov ba38f3becc
rpc : proper handling of data pointers to CPU buffers (#21030)
The compute graph may contain tensors pointing to CPU buffers. In these
cases the buffer address is serialized as 0 and sent over the wire.
However, the data pointer is serialized as-is and this prevents proper
validation on the server side. This patches fixes this by serializing
the data pointer as 0 for non-RPC buffers and doing proper validation on
the server side.

closes: #21006
2026-03-27 10:59:35 +02:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include llama: fix llama-model-saver (#20503) 2026-03-25 12:53:16 +02:00
src rpc : proper handling of data pointers to CPU buffers (#21030) 2026-03-27 10:59:35 +02:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml : bump version to 0.9.8 (ggml/1442) 2026-03-18 15:17:28 +02:00