[RFC] Replace shared-memory routed experts with ModelRunnerOutput transfer and HTTP support (#39568)
Signed-off-by: xhx1022 <1737006628@qq.com> Signed-off-by: arlenxu <arlenxu@tencent.com> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Co-authored-by: arlenxu <arlenxu@tencent.com> Co-authored-by: Junjie Zhang <junj.jay.zhang@gmail.com>
This commit is contained in:
co-authored by
Claude Opus 4.6
arlenxu
Junjie Zhang
parent
2317682f95
commit
c7560af424
@@ -282,6 +282,7 @@ def test_abort_request_when_structured_output_fsm_cannot_advance():
|
||||
scheduler.finished_req_ids_dict = None
|
||||
scheduler.vllm_config = Mock()
|
||||
scheduler.vllm_config.model_config.enable_return_routed_experts = False
|
||||
scheduler.enable_return_routed_experts = False
|
||||
scheduler.recompute_kv_load_failures = False
|
||||
scheduler.make_stats = Mock(return_value=None)
|
||||
scheduler.max_model_len = 128
|
||||
|
||||
@@ -2545,6 +2545,7 @@ def test_abort_request_when_structured_output_fsm_cannot_advance():
|
||||
scheduler.finished_req_ids_dict = None
|
||||
scheduler.vllm_config = Mock()
|
||||
scheduler.vllm_config.model_config.enable_return_routed_experts = False
|
||||
scheduler.enable_return_routed_experts = False
|
||||
scheduler.recompute_kv_load_failures = False
|
||||
scheduler.make_stats = Mock(return_value=None)
|
||||
scheduler.max_model_len = 128
|
||||
|
||||
Reference in New Issue
Block a user