Clean up server_args, triton cache manager (#8332)
This commit is contained in:
@@ -261,7 +261,7 @@ class TestMTP(CustomTestCase):
|
||||
"--enable-dp-lm-head",
|
||||
"--enable-deepep-moe",
|
||||
"--speculative-algo",
|
||||
"NEXTN",
|
||||
"EAGLE",
|
||||
"--speculative-draft",
|
||||
DEFAULT_MODEL_NAME_FOR_TEST_MLA_NEXTN,
|
||||
"--speculative-num-steps",
|
||||
@@ -329,7 +329,7 @@ class TestMTPWithTBO(CustomTestCase):
|
||||
"--enable-deepep-moe",
|
||||
"--trust-remote-code",
|
||||
"--speculative-algorithm",
|
||||
"NEXTN",
|
||||
"EAGLE",
|
||||
"--speculative-num-steps",
|
||||
"2",
|
||||
"--speculative-eagle-topk",
|
||||
|
||||
Reference in New Issue
Block a user