spec: STANDALONE skips hidden_states end-to-end (Optional schema + None-safe consumers) (#25037)
Co-authored-by: Qiaolin Yu <qy254@cornell.edu>
This commit is contained in:
co-authored by
Qiaolin Yu
parent
e86fb42736
commit
538832c8b7
@@ -6,6 +6,7 @@ import requests
|
||||
from sglang.srt.environ import envs
|
||||
from sglang.srt.utils import kill_process_tree
|
||||
from sglang.test.ci.ci_register import register_cuda_ci
|
||||
from sglang.test.kits.radix_cache_server_kit import run_radix_attention_test
|
||||
from sglang.test.run_eval import run_eval
|
||||
from sglang.test.test_utils import (
|
||||
DEFAULT_DRAFT_MODEL_STANDALONE,
|
||||
@@ -205,6 +206,10 @@ class TestStandaloneV2SpeculativeDecodingTriton(
|
||||
def get_server_args(cls):
|
||||
return DEFAULT_SERVER_ARGS_V2 + ["--attention-backend", "triton"]
|
||||
|
||||
def test_radix_attention(self):
|
||||
run_radix_attention_test(self.base_url)
|
||||
assert self.process.poll() is None
|
||||
|
||||
|
||||
class TestStandaloneV2SpeculativeDecodingFlashinfer(
|
||||
TestStandaloneV2SpeculativeDecodingBase
|
||||
|
||||
Reference in New Issue
Block a user