[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:
Hongxin Xu
2026-05-14 14:12:30 +00:00
committed by GitHub
co-authored by Claude Opus 4.6 arlenxu Junjie Zhang
parent 2317682f95
commit c7560af424
12 changed files with 605 additions and 369 deletions
+1
View File
@@ -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
+1
View File
@@ -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