fix(spec_v2): support EAGLE with spec_v2

1. add pass for spec_v2 in base_attn 2. fix: EAGLE with spec_v2 overlap Grammar accept_token failed Signed-off-by: wxiwnd <wxiwnd@outlook.com>
2026-04-09 01:37:13 +08:00
parent 101100e25b
commit ef607c35c9
3 changed files with 124 additions and 14 deletions
@@ -0,0 +1,85 @@
+"""Unit tests for overlap disaggregation decode event loop ordering."""
+
+import unittest
+from types import SimpleNamespace
+from typing import Any, cast
+
+from sglang.srt.disaggregation.decode import SchedulerDisaggregationDecodeMixin
+from sglang.test.ci.ci_register import register_cpu_ci
+from sglang.test.test_utils import CustomTestCase
+
+register_cpu_ci(est_time=6, suite="stage-a-test-cpu")
+
+
+class FakeBatch:
+    def __init__(self, label: str):
+        self.label = label
+
+    def copy(self):
+        return self
+
+
+class TestOverlapDisaggDecodeEventLoop(CustomTestCase):
+    def test_processes_previous_result_before_disabled_overlap_launch(self):
+        class StopLoop(Exception):
+            pass
+
+        batch1 = FakeBatch("batch-1")
+        batch2 = FakeBatch("batch-2")
+        batches = iter([batch1, batch2])
+        events = []
+
+        def get_next_batch():
+            return next(batches)
+
+        def run_batch(batch):
+            result = f"result-{batch.label}"
+            events.append(f"run:{batch.label}")
+            return result
+
+        def process_batch_result(batch, result):
+            events.append(f"process:{batch.label}")
+
+        def launch_batch_sample_if_needed(result):
+            events.append(f"sample:{result}")
+            if result == "result-batch-2":
+                raise StopLoop()
+
+        scheduler = cast(
+            Any,
+            SimpleNamespace(
+                recv_requests=lambda: [],
+                process_input_requests=lambda reqs: None,
+                process_decode_queue=lambda: None,
+                get_next_disagg_decode_batch_to_run=get_next_batch,
+                run_batch=run_batch,
+                process_batch_result=process_batch_result,
+                is_disable_overlap_for_batch=lambda batch: batch is batch2,
+                launch_batch_sample_if_needed=launch_batch_sample_if_needed,
+                self_check_during_idle=lambda: None,
+            ),
+        )
+
+        with self.assertRaises(StopLoop):
+            SchedulerDisaggregationDecodeMixin.event_loop_overlap_disagg_decode(
+                scheduler
+            )
+
+        self.assertEqual(
+            events,
+            [
+                "run:batch-1",
+                "sample:result-batch-1",
+                "process:batch-1",
+                "run:batch-2",
+                "sample:result-batch-2",
+            ],
+        )
+        self.assertEqual(len(scheduler.result_queue), 1)
+        queued_batch, queued_result = scheduler.result_queue[0]
+        self.assertIs(queued_batch, batch2)
+        self.assertEqual(queued_result, "result-batch-2")
+
+
+if __name__ == "__main__":
+    unittest.main()