[Config Refactor][2/N] Pipeline + Deploy Config Schema (#2383)

Signed-off-by: lishunyang <lishunyang12@163.com>
Signed-off-by: reidliu41 <reid201711@gmail.com>
Signed-off-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: xiaohajiayou <75477391+xiaohajiayou@users.noreply.github.com>
Co-authored-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
authored and GitHub committed 2026-04-19 14:36:00 +12:00
1 parent a683b1dd75
commit a3903810fe
104 files changed
+3959 -3814

No files matched your search

+10 -4
View File
@@ -48,8 +48,8 @@ BENCHMARK_CONFIGS = load_configs(CONFIG_FILE_PATH)
OMNI_RESULT_TEMPLATE_PATH = Path(__file__).parent / "result_omni_template.json"
STAGE_CONFIGS_DIR = Path(__file__).parent.parent / "stage_configs"
test_params = create_unique_server_params(BENCHMARK_CONFIGS, STAGE_CONFIGS_DIR)
DEPLOY_CONFIGS_DIR = Path(__file__).parent.parent / "deploy"
test_params = create_unique_server_params(BENCHMARK_CONFIGS, DEPLOY_CONFIGS_DIR)
server_to_benchmark_mapping = create_test_parameter_mapping(BENCHMARK_CONFIGS)
_omni_server_lock = threading.Lock()
@@ -62,13 +62,19 @@ def omni_server(request):
Multi-stage initialization can take 10-20+ minutes.
"""
with _omni_server_lock:
test_name, model, stage_config_path = request.param
test_name, model, stage_config_path, stage_overrides, extra_cli_args = request.param
print(f"Starting OmniServer with test: {test_name}, model: {model}")
server_args = ["--stage-init-timeout", "600", "--init-timeout", "900"]
# --deploy-config and --stage-overrides compose at the CLI (see vllm_omni/entrypoints/utils.py):
# deploy-config sets the base; stage-overrides are applied on top. Both can be set.
if stage_config_path:
server_args = ["--stage-configs-path", stage_config_path] + server_args
server_args = ["--deploy-config", stage_config_path] + server_args
if stage_overrides:
server_args = ["--stage-overrides", stage_overrides] + server_args
if extra_cli_args:
server_args = list(extra_cli_args) + server_args
with OmniServer(model, server_args) as server:
server.test_name = test_name
print("OmniServer started successfully")