Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ci : add PYTEST_WORKERS=1 to fix server-self-hosted job (#28603)

Browse Source 
* ci : add PYTEST_WORKERS=1 to fix server-self-hosted job

This commit adds the `PYTEST_WORKERS=1` environment variable to the
hf-jobs-t4-small:cuda13 runner steps.

This is an attempt to address CI failure of this job that I might have
introduced in Commit 42f0225fea
("server : use pytest-xdist for server tests (#28298)").

Refs: https://github.com/ggml-org/llama.cpp/actions/runs/34126971262/job/101757819134

* apply same changes to server-metal steps
This commit is contained in:
Daniel Bevenius
2026-09-08 13:36:03 +02:00
committed by GitHub
parent ca86fb222e
commit 1744c6bde8
1 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/server-self-hosted.yml
+8 -8
View File
@@ -72,7 +72,7 @@ jobs:
run: | run: |
cd tools/server/tests cd tools/server/tests
source venv/bin/activate source venv/bin/activate
./tests.sh PYTEST_WORKERS=1 ./tests.sh
- name: Tests (GPUx1, backend-sampling) - name: Tests (GPUx1, backend-sampling)
id: server_integration_tests_backend_sampling id: server_integration_tests_backend_sampling
@@ -81,7 +81,7 @@ jobs:
cd tools/server/tests cd tools/server/tests
source venv/bin/activate source venv/bin/activate
export LLAMA_ARG_BACKEND_SAMPLING=1 export LLAMA_ARG_BACKEND_SAMPLING=1
./tests.sh PYTEST_WORKERS=1 ./tests.sh
- name: Tests (GPUx2) - name: Tests (GPUx2)
id: server_integration_tests_gpu2 id: server_integration_tests_gpu2
@@ -90,7 +90,7 @@ jobs:
cd tools/server/tests cd tools/server/tests
source venv/bin/activate source venv/bin/activate
export GGML_METAL_DEVICES=2 export GGML_METAL_DEVICES=2
./tests.sh PYTEST_WORKERS=1 ./tests.sh
- name: Tests (GPUx2, backend-sampling) - name: Tests (GPUx2, backend-sampling)
id: server_integration_tests_gpu2_backend_sampling id: server_integration_tests_gpu2_backend_sampling
@@ -99,7 +99,7 @@ jobs:
cd tools/server/tests cd tools/server/tests
source venv/bin/activate source venv/bin/activate
export GGML_METAL_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1 export GGML_METAL_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1
./tests.sh PYTEST_WORKERS=1 ./tests.sh
server-cuda: server-cuda:
runs-on: "hf-jobs-t4-small:cuda13" runs-on: "hf-jobs-t4-small:cuda13"
@@ -162,7 +162,7 @@ jobs:
run: | run: |
cd tools/server/tests cd tools/server/tests
source venv/bin/activate source venv/bin/activate
./tests.sh PYTEST_WORKERS=1 ./tests.sh
- name: Tests (GPUx1, backend-sampling) - name: Tests (GPUx1, backend-sampling)
id: server_integration_tests_backend_sampling id: server_integration_tests_backend_sampling
@@ -171,7 +171,7 @@ jobs:
cd tools/server/tests cd tools/server/tests
source venv/bin/activate source venv/bin/activate
export LLAMA_ARG_BACKEND_SAMPLING=1 export LLAMA_ARG_BACKEND_SAMPLING=1
./tests.sh PYTEST_WORKERS=1 ./tests.sh
- name: Tests (GPUx2) - name: Tests (GPUx2)
id: server_integration_tests_gpu2 id: server_integration_tests_gpu2
@@ -180,7 +180,7 @@ jobs:
cd tools/server/tests cd tools/server/tests
source venv/bin/activate source venv/bin/activate
export GGML_CUDA_DEVICES=2 export GGML_CUDA_DEVICES=2
./tests.sh PYTEST_WORKERS=1 ./tests.sh
- name: Tests (GPUx2, backend-sampling) - name: Tests (GPUx2, backend-sampling)
id: server_integration_tests_gpu2_backend_sampling id: server_integration_tests_gpu2_backend_sampling
@@ -189,7 +189,7 @@ jobs:
cd tools/server/tests cd tools/server/tests
source venv/bin/activate source venv/bin/activate
export GGML_CUDA_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1 export GGML_CUDA_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1
./tests.sh PYTEST_WORKERS=1 ./tests.sh
server-kleidiai: server-kleidiai:
runs-on: ah-ubuntu_22_04-c8g_8x runs-on: ah-ubuntu_22_04-c8g_8x