Gate CP shared-KV prefill batching behind explicit limits

The scheduler can now admit multi-request NSA in-seq CP shared-KV prefill batches only when the shared-KV bs>1 flag is explicitly enabled. The gate is still disabled by default and is scoped to CP shared-KV so ordinary CP is not widened accidentally.

Batch admission is bounded by optional request-count and page-aligned extend-token limits while real memory capacity remains allocator-owned. This keeps bf16 and fp8 on the same scheduler path because dtype differences are already reflected in KV pool token/page capacity.

Constraint: bs>1 runtime paths remain guarded by existing CP shared-KV fail-fast checks.

Constraint: Scheduler must not duplicate bf16/fp8 byte-level capacity estimation.

Rejected: Open the old CP gate unconditionally | ordinary CP would inherit an unverified shared-KV-specific batching path.

Rejected: Treat the extend-token cap as a hard per-request limit | a single large request could deadlock the scheduler.

Confidence: medium

Scope-risk: moderate

Directive: Keep CP shared-KV batching gated until ETE validates EAGLE accept length, output length, and HiCache load/backup behavior under real traffic.

Tested: local py_compile for server_args, schedule_policy, scheduler, prefill_adder tests, and server_args tests.

Tested: remote g0034 py_compile for the same files.

Tested: remote g0034 pytest target set: 5 passed for parser, parameter validation, default single-request CP gate, enabled bs>1 gate, and page-aligned extend cap.

Tested: remote g0034 pytest test_prefill_adder.py => 13 passed.

Not-tested: full server_args test file has an unrelated HuggingFace DNS/config-download failure in TestPrepareServerArgs.test_prepare_server_args.

Not-tested: ETE production traffic with --enable-cp-shared-kv-prefill-bs-gt1.

test/registered/unit/server_args/test_server_args.py

@@ -53,6 +53,28 @@ def test_enable_nsa_prefill_cp_shared_kv_parser_flag():
     assert args.enable_nsa_prefill_cp_shared_kv is True
 
 
+def test_cp_shared_kv_prefill_bs_gt1_parser_limits():
+    import argparse
+
+    parser = argparse.ArgumentParser()
+    ServerArgs.add_cli_args(parser)
+    raw_args = parser.parse_args(
+        [
+            "--model-path",
+            "dummy",
+            "--enable-cp-shared-kv-prefill-bs-gt1",
+            "--cp-shared-kv-prefill-max-batch-requests",
+            "4",
+            "--cp-shared-kv-prefill-max-total-extend-tokens",
+            "8192",
+        ]
+    )
+    args = ServerArgs.from_cli_args(raw_args)
+    assert args.enable_cp_shared_kv_prefill_bs_gt1 is True
+    assert args.cp_shared_kv_prefill_max_batch_requests == 4
+    assert args.cp_shared_kv_prefill_max_total_extend_tokens == 8192
+
+
 class TestLoadBalanceMethod(unittest.TestCase):
     def test_non_pd_defaults_to_round_robin(self):
         server_args = ServerArgs(model_path="dummy", disaggregation_mode="null")
@@ -438,6 +460,23 @@ class TestHiCacheArgs(CustomTestCase):
                 enable_hisparse=False,
             )
 
+    def test_cp_shared_kv_prefill_batch_limits_must_be_positive(self):
+        with self.assertRaisesRegex(
+            ValueError, "cp_shared_kv_prefill_max_batch_requests.*positive"
+        ):
+            ServerArgs(
+                model_path="dummy",
+                cp_shared_kv_prefill_max_batch_requests=0,
+            )
+
+        with self.assertRaisesRegex(
+            ValueError, "cp_shared_kv_prefill_max_total_extend_tokens.*positive"
+        ):
+            ServerArgs(
+                model_path="dummy",
+                cp_shared_kv_prefill_max_total_extend_tokens=0,
+            )
+
     def test_hicache_io_backend_and_mem_layout_compatibility(self):
         cases = [
             {