[diffusion] feat: add performance mode server args (#24491)
This commit is contained in:
@@ -51,9 +51,10 @@ class ServerWithGrammar(CustomTestCase):
|
||||
"--speculative-num-draft-tokens=8",
|
||||
]
|
||||
|
||||
with envs.SGLANG_SPEC_NAN_DETECTION.override(
|
||||
True
|
||||
), envs.SGLANG_SPEC_OOB_DETECTION.override(True):
|
||||
with (
|
||||
envs.SGLANG_SPEC_NAN_DETECTION.override(True),
|
||||
envs.SGLANG_SPEC_OOB_DETECTION.override(True),
|
||||
):
|
||||
cls.process = popen_launch_server(
|
||||
cls.model,
|
||||
cls.base_url,
|
||||
|
||||
Reference in New Issue
Block a user