llama.cpp/ggml
Diego Devesa e072b2052e
ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276)
* ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched
Enabled in ggml-ci for testing.

* llama : update worst-case graph for unified cache

* ci : disable op offload in some tests

* fix spelling

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-11-28 17:33:23 +02:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include rpc : cache and reuse compute graphs (#15405) 2025-11-28 08:33:51 +00:00
src ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276) 2025-11-28 17:33:23 +02:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276) 2025-11-28 17:33:23 +02:00