feat: Session-reference-aware Unified Radix Cache for agentic multi-turn workloads (#29173)
Co-authored-by: Ishan Dhanani <ishandhanani@gmail.com> Co-authored-by: hzh0425 <hzh0425@apache.org> Co-authored-by: ispobock <ispobaoke@gmail.com>
This commit is contained in:
co-authored by
Ishan Dhanani
hzh0425
ispobock
parent
131bd51b01
commit
056474cdb0
@@ -1274,17 +1274,6 @@ class TestPrefillOnlyDisableKvCache(unittest.TestCase):
|
||||
self._validate_prefill_only_args(kv_cache_dtype=kv_cache_dtype)
|
||||
|
||||
|
||||
class TestSessionRadixCacheServerArgs(unittest.TestCase):
|
||||
def test_requires_priority_radix_eviction_policy(self):
|
||||
server_args = ServerArgs(
|
||||
model_path="dummy",
|
||||
enable_session_radix_cache=True,
|
||||
radix_eviction_policy="lru",
|
||||
)
|
||||
with self.assertRaisesRegex(ValueError, "--radix-eviction-policy priority"):
|
||||
server_args._handle_cache_compatibility()
|
||||
|
||||
|
||||
class TestCudaGraphConfigDataclassAccess(CustomTestCase):
|
||||
@patch(
|
||||
"sglang.srt.model_executor.runner_backend."
|
||||
|
||||
Reference in New Issue
Block a user