LLM inference in C/C++
C++ ggml
ci: bump kleidiai runners from 22.04 to 24.04 (#28885)
Aaron Teo1af6c65de09e
diff --git a/.github/workflows/build-self-hosted.yml b/.github/workflows/build-self-hosted.ymlindex 2e05988bf7..1337a0ed5b 100644--- a/.github/workflows/build-self-hosted.yml+++ b/.github/workflows/build-self-hosted.yml@@ -361,7 +361,7 @@ jobs:LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cppcpu-arm64-high-perf-graviton4:- runs-on: ah-ubuntu_22_04-c8g_8x+ runs-on: ah-ubuntu_24_04-c8g_8xsteps:- name: Clone@@ -404,7 +404,7 @@ jobs:bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cppcpu-arm64-graviton4-kleidiai:- runs-on: ah-ubuntu_22_04-c8g_8x+ runs-on: ah-ubuntu_24_04-c8g_8xsteps:- name: Clonediff --git a/.github/workflows/server-self-hosted.yml b/.github/workflows/server-self-hosted.ymlindex de30d1a749..8dc4637c45 100644--- a/.github/workflows/server-self-hosted.yml+++ b/.github/workflows/server-self-hosted.yml@@ -192,7 +192,7 @@ jobs:PYTEST_WORKERS=1 ./tests.shserver-kleidiai:- runs-on: ah-ubuntu_22_04-c8g_8x+ runs-on: ah-ubuntu_24_04-c8g_8xsteps:- name: Clone@@ -232,7 +232,7 @@ jobs:- name: Buildid: cmake_buildrun: |- cmake -B build -DGGML_SCHED_NO_REALLOC=ON -DGGML_CPU_KLEIDIAI=ON+ cmake -B build -DGGML_SCHED_NO_REALLOC=ON -DGGML_CPU_KLEIDIAI=ON -DLLAMA_FATAL_WARNINGS=ONcmake --build build --config Release -j $(nproc) --target llama-server- name: Python setup