ci: prune per-commit CUDA tests — move 25 files + 13 testcases to test/manual/ (#24721)

test/manual/4-gpu-models/test_qwen3_next_models.py

@@ -0,0 +1,34 @@
+import unittest
+
+from sglang.test.ci.ci_register import register_cuda_ci
+from sglang.test.kits.eval_accuracy_kit import GSM8KMixin
+from sglang.test.kits.kl_divergence_kit import KLDivergenceMixin
+from sglang.test.kits.prefix_cache_branching_kit import PrefixCacheBranchingMixin
+from sglang.test.server_fixtures.default_fixture import DefaultServerBase
+
+register_cuda_ci(est_time=142, suite="stage-c-test-4-gpu-h100")
+
+QWEN3_NEXT_MODEL = "Qwen/Qwen3-Next-80B-A3B-Instruct"
+
+
+class TestQwen3Next(
+    GSM8KMixin, KLDivergenceMixin, PrefixCacheBranchingMixin, DefaultServerBase
+):
+    model = QWEN3_NEXT_MODEL
+    cache_chunk_size = 64
+    gsm8k_accuracy_thres = 0.93
+    kl_div_thres = 0.0025
+    other_args = [
+        "--tp-size",
+        "4",
+        "--chunked-prefill-size",
+        "2048",
+        "--mamba-scheduler-strategy",
+        "extra_buffer",
+        "--mamba-track-interval",
+        "128",
+    ]
+
+
+if __name__ == "__main__":
+    unittest.main()