anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Refactor] Remove legacy --stage-configs-path from the serve CLI (#5647)

Browse Source 
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
This commit is contained in:
Yukim1 authored and GitHub committed 2026-08-03 23:41:52 +08:00
1 parent 76de642c54
commit 7a2007cc17
29 files changed
+113 -108
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/dfx/reliability/test_reliability_qwen3_omni.py
+7 -7
View File
@@ -241,12 +241,12 @@ def _fault_keywords_match_response(*, status: int, body: bytes) -> bool:
return any(key in text for key in body_fault_hints)
def _stage_config_path_from_omni_server(omni_server: _HasServeArgs) -> str | None:
def _deploy_config_path_from_omni_server(omni_server: _HasServeArgs) -> str | None:
args: list[str] = omni_server.serve_args
for i, arg in enumerate(args):
if arg == "--stage-configs-path" and i + 1 < len(args):
if arg == "--deploy-config" and i + 1 < len(args):
return args[i + 1]
if arg.startswith("--stage-configs-path="):
if arg.startswith("--deploy-config="):
return arg.split("=", 1)[1]
return None
@@ -331,7 +331,7 @@ def test_reliability_fault_gpu_oom_error_contract_consistent_chat_speech(
"""
device_spec = resolve_oom_device_spec(
OOM_INJECTION_CONFIG,
_stage_config_path_from_omni_server(omni_server_function),
_deploy_config_path_from_omni_server(omni_server_function),
)
handle = inject_gpu_oom(
device=device_spec,
@@ -394,7 +394,7 @@ def test_reliability_fault_gpu_oom_error_contract_consistent_chat_speech(
def test_reliability_fault_gpu_oom_chat_large_payload_failure(omni_server_function, openai_client_function) -> None:
device_spec = resolve_oom_device_spec(
OOM_INJECTION_CONFIG,
_stage_config_path_from_omni_server(omni_server_function),
_deploy_config_path_from_omni_server(omni_server_function),
)
handle = inject_gpu_oom(
device=device_spec,
@@ -437,7 +437,7 @@ def test_reliability_fault_gpu_oom_chat_large_payload_failure(omni_server_functi
def test_reliability_fault_gpu_oom_concurrent_pressure_failure(omni_server_function, openai_client_function) -> None:
device_spec = resolve_oom_device_spec(
OOM_INJECTION_CONFIG,
_stage_config_path_from_omni_server(omni_server_function),
_deploy_config_path_from_omni_server(omni_server_function),
)
handle = inject_gpu_oom(
device=device_spec,
@@ -791,7 +791,7 @@ def test_reliability_fault_gpu_oom_state_converges_after_fault_removed(
"""
device_spec = resolve_oom_device_spec(
OOM_RECOVER_INJECTION_CONFIG,
_stage_config_path_from_omni_server(omni_server_function),
_deploy_config_path_from_omni_server(omni_server_function),
)
handle = inject_gpu_oom(
device=device_spec,