LLM inference in C/C++
C++ ggml
ci : add PYTEST_WORKERS=1 to fix server-self-hosted job (#28603)
Daniel Bevenius1744c6bde8d6
diff --git a/.github/workflows/server-self-hosted.yml b/.github/workflows/server-self-hosted.ymlindex d9ad2fcd0d..de30d1a749 100644--- a/.github/workflows/server-self-hosted.yml+++ b/.github/workflows/server-self-hosted.yml@@ -72,7 +72,7 @@ jobs:run: |cd tools/server/testssource venv/bin/activate- ./tests.sh+ PYTEST_WORKERS=1 ./tests.sh- name: Tests (GPUx1, backend-sampling)id: server_integration_tests_backend_sampling@@ -81,7 +81,7 @@ jobs:cd tools/server/testssource venv/bin/activateexport LLAMA_ARG_BACKEND_SAMPLING=1- ./tests.sh+ PYTEST_WORKERS=1 ./tests.sh- name: Tests (GPUx2)id: server_integration_tests_gpu2@@ -90,7 +90,7 @@ jobs:cd tools/server/testssource venv/bin/activateexport GGML_METAL_DEVICES=2- ./tests.sh+ PYTEST_WORKERS=1 ./tests.sh- name: Tests (GPUx2, backend-sampling)id: server_integration_tests_gpu2_backend_sampling@@ -99,7 +99,7 @@ jobs:cd tools/server/testssource venv/bin/activateexport GGML_METAL_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1- ./tests.sh+ PYTEST_WORKERS=1 ./tests.shserver-cuda:runs-on: "hf-jobs-t4-small:cuda13"@@ -162,7 +162,7 @@ jobs:run: |cd tools/server/testssource venv/bin/activate- ./tests.sh+ PYTEST_WORKERS=1 ./tests.sh- name: Tests (GPUx1, backend-sampling)id: server_integration_tests_backend_sampling@@ -171,7 +171,7 @@ jobs:cd tools/server/testssource venv/bin/activateexport LLAMA_ARG_BACKEND_SAMPLING=1- ./tests.sh+ PYTEST_WORKERS=1 ./tests.sh- name: Tests (GPUx2)id: server_integration_tests_gpu2@@ -180,7 +180,7 @@ jobs:cd tools/server/testssource venv/bin/activateexport GGML_CUDA_DEVICES=2- ./tests.sh+ PYTEST_WORKERS=1 ./tests.sh- name: Tests (GPUx2, backend-sampling)id: server_integration_tests_gpu2_backend_sampling@@ -189,7 +189,7 @@ jobs:cd tools/server/testssource venv/bin/activateexport GGML_CUDA_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1- ./tests.sh+ PYTEST_WORKERS=1 ./tests.shserver-kleidiai:runs-on: ah-ubuntu_22_04-c8g_8x