LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity

tests : clean-up server test, use tests.sh in ci (#26886)

Browse Source 
* tests : remove fetch_server_test_models.py

* ci : use tests.sh wrapper of pytest
This commit is contained in:
Georgi Gerganov
2026-08-11 09:07:13 +03:00
committed by GitHub
parent 4801e3c567
commit b3df57286c
5 changed files with 17 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/server-sanitize.yml
+2 -2
View File
@@ -110,7 +110,7 @@ jobs:
source .venv/bin/activate
cd tools/server/tests
export ${{ matrix.extra_args }}
pytest -v -x -m "not slow"
./tests.sh
- name: Slow tests
id: server_integration_tests_slow
@@ -119,4 +119,4 @@ jobs:
source .venv/bin/activate
cd tools/server/tests
export ${{ matrix.extra_args }}
SLOW_TESTS=1 pytest -v -x
SLOW_TESTS=1 ./tests.sh
.github/workflows/server-self-hosted.yml
+9 -9
View File
@@ -72,7 +72,7 @@ jobs:
run: |
cd tools/server/tests
source venv/bin/activate
pytest -v -x -m "not slow"
./tests.sh
- name: Tests (GPUx1, backend-sampling)
id: server_integration_tests_backend_sampling
@@ -81,7 +81,7 @@ jobs:
cd tools/server/tests
source venv/bin/activate
export LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
./tests.sh
- name: Tests (GPUx2)
id: server_integration_tests_gpu2
@@ -90,7 +90,7 @@ jobs:
cd tools/server/tests
source venv/bin/activate
export GGML_METAL_DEVICES=2
pytest -v -x -m "not slow"
./tests.sh
- name: Tests (GPUx2, backend-sampling)
id: server_integration_tests_gpu2_backend_sampling
@@ -99,7 +99,7 @@ jobs:
cd tools/server/tests
source venv/bin/activate
export GGML_METAL_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
./tests.sh
server-cuda:
runs-on: [self-hosted, llama-server, Linux, NVIDIA]
@@ -132,7 +132,7 @@ jobs:
run: |
cd tools/server/tests
source venv/bin/activate
pytest -v -x -m "not slow"
./tests.sh
- name: Tests (GPUx1, backend-sampling)
id: server_integration_tests_backend_sampling
@@ -141,7 +141,7 @@ jobs:
cd tools/server/tests
source venv/bin/activate
export LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
./tests.sh
- name: Tests (GPUx2)
id: server_integration_tests_gpu2
@@ -150,7 +150,7 @@ jobs:
cd tools/server/tests
source venv/bin/activate
export GGML_CUDA_DEVICES=2
pytest -v -x -m "not slow"
./tests.sh
- name: Tests (GPUx2, backend-sampling)
id: server_integration_tests_gpu2_backend_sampling
@@ -159,7 +159,7 @@ jobs:
cd tools/server/tests
source venv/bin/activate
export GGML_CUDA_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
./tests.sh
server-kleidiai:
runs-on: ah-ubuntu_22_04-c8g_8x
@@ -219,4 +219,4 @@ jobs:
run: |
cd tools/server/tests
source venv/bin/activate
pytest -v -x -m "not slow"
./tests.sh
.github/workflows/server.yml
+6 -6
View File
@@ -104,21 +104,21 @@ jobs:
id: server_integration_tests
run: |
cd tools/server/tests
pytest -v -x -m "not slow"
./tests.sh
- name: Slow tests
id: server_integration_tests_slow
if: ${{ github.event.schedule || github.event.inputs.slow_tests == 'true' }}
run: |
cd tools/server/tests
SLOW_TESTS=1 pytest -v -x
SLOW_TESTS=1 ./tests.sh
- name: Tests (Backend sampling)
id: server_integration_tests_backend_sampling
run: |
cd tools/server/tests
export LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
./tests.sh
- name: Slow tests (Backend sampling)
id: server_integration_tests_slow_backend_sampling
@@ -126,7 +126,7 @@ jobs:
run: |
cd tools/server/tests
export LLAMA_ARG_BACKEND_SAMPLING=1
SLOW_TESTS=1 pytest -v -x
SLOW_TESTS=1 ./tests.sh
windows:
runs-on: windows-2025
@@ -170,7 +170,7 @@ jobs:
run: |
cd tools/server/tests
$env:PYTHONIOENCODING = ":replace"
pytest -v -x -m "not slow"
./tests.sh
- name: Slow tests
id: server_integration_tests_slow
@@ -178,4 +178,4 @@ jobs:
run: |
cd tools/server/tests
$env:SLOW_TESTS = "1"
pytest -v -x
./tests.sh