[Feat][GLM5.2] Add DSA Cache Layer Split under Prefill CP (#29421)
Signed-off-by: Shijin Zhang <75300765+Dovis01@users.noreply.github.com>
This commit is contained in:
@@ -114,6 +114,7 @@ def _make_model_runner(
|
||||
sa.disaggregation_mode = disaggregation_mode
|
||||
sa.max_running_requests = max_running_requests
|
||||
sa.disaggregation_decode_extra_slots = disaggregation_decode_extra_slots
|
||||
sa.enable_dsa_cache_layer_split = False
|
||||
mr.server_args = sa
|
||||
|
||||
spec = MagicMock()
|
||||
|
||||
Reference in New Issue
Block a user