]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sche...
authorDiego Devesa <redacted>
Fri, 28 Nov 2025 15:33:23 +0000 (07:33 -0800)
committerGitHub <redacted>
Fri, 28 Nov 2025 15:33:23 +0000 (17:33 +0200)
commite072b2052e9250395e4a28a28d37806342ac5db1
tree37daf9e852c33c1001862c0c590e05dc9cc57af7
parentc6f7a423c8c87748ef563a99d81c3b1b05cecff0
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 <redacted>
ci/run.sh
examples/embedding/embedding.cpp
ggml/CMakeLists.txt
ggml/src/CMakeLists.txt
ggml/src/ggml-alloc.c
ggml/src/ggml-backend.cpp
src/llama-context.cpp
tests/CMakeLists.txt