Preserve FP8 CP shared-KV page contracts

NSA FP8 CP shared-KV reuse must operate on packed page-slot rows, not bf16 compact rows. The change keeps current-only and partial-current reuse inside the page-aligned materialization contract, fails fast for non-page-aligned CP split inputs, and prevents FP8 FlashMLA-KV prefill from reaching incompatible in-seq CP metadata.

Constraint: NSA FP8 persistent MLA KV rows are packed 656-byte records and CP shared KV cache management is page-granular.\nConstraint: FlashMLA-KV prefill metadata is not CP-local after NSA in-seq splitting.\nRejected: Silently splice bf16 current rows into FP8 materialized cache | corrupts the packed cache layout.\nRejected: Keep FP8 FlashMLA-KV auto prefill under NSA CP | reaches num_splits shape errors after q-row splitting.\nConfidence: medium\nScope-risk: moderate\nDirective: Do not re-enable FP8 FlashMLA-KV prefill for NSA in-seq CP until metadata is rebuilt after CP splitting or made CP-local.\nTested: Local git diff --check and py_compile for touched SGLang files.\nTested: Remote g0034 related unit sweep recorded in docs: test_nsa_cp_utils.py, test_cp_shared_kv_layout.py, test_cp_shared_kv_runtime.py, test_cp_hicache_metadata.py passed.\nNot-tested: Full FP8 ETE startup and performance run after this commit.

test/registered/unit/layers/test_nsa_cp_utils.py

@@ -283,6 +283,62 @@ class TestNSAInSeqCPUtils(unittest.TestCase):
         ):
             self.assertFalse(can_cp_split(256, 8, True, forward_batch))
 
+    def test_can_cp_split_skips_current_only_when_page_units_do_not_cover_all_lanes(
+        self,
+    ):
+        class Mode:
+            def is_context_parallel_extend(self):
+                return True
+
+        forward_batch = SimpleNamespace(
+            uses_cp_shared_kv=True,
+            extend_seq_lens_cpu=[64],
+            extend_prefix_lens_cpu=[0],
+            token_to_kv_pool=SimpleNamespace(page_size=64),
+            forward_mode=Mode(),
+        )
+
+        with (
+            patch(
+                "sglang.srt.layers.attention.nsa.utils.is_nsa_prefill_cp_round_robin_split",
+                return_value=False,
+            ),
+            patch(
+                "sglang.srt.layers.attention.nsa.utils.is_nsa_enable_prefill_cp",
+                return_value=True,
+            ),
+        ):
+            self.assertFalse(can_cp_split(64, 8, True, forward_batch))
+
+    def test_can_cp_split_fails_on_non_page_aligned_cp_shared_prefix(self):
+        class Mode:
+            def is_context_parallel_extend(self):
+                return True
+
+        forward_batch = SimpleNamespace(
+            uses_cp_shared_kv=True,
+            extend_seq_lens_cpu=[1024],
+            extend_prefix_lens_cpu=[65],
+            token_to_kv_pool=SimpleNamespace(page_size=64),
+            forward_mode=Mode(),
+        )
+
+        with (
+            patch(
+                "sglang.srt.layers.attention.nsa.utils.is_nsa_prefill_cp_round_robin_split",
+                return_value=False,
+            ),
+            patch(
+                "sglang.srt.layers.attention.nsa.utils.is_nsa_enable_prefill_cp",
+                return_value=True,
+            ),
+            self.assertRaisesRegex(
+                RuntimeError,
+                r"\[CP_SHARED_KV_FAIL_FAST\]\[cp_split_non_page_aligned_prefix\]",
+            ),
+        ):
+            can_cp_split(1089, 8, True, forward_batch)
+
     def test_can_cp_split_keeps_cp_for_radix_hit_suffix_with_one_page_per_rank(self):
         class Mode:
             def is_context_parallel_extend(self):
@@ -653,10 +709,18 @@ class TestNSAInSeqCPUtils(unittest.TestCase):
         indexer._maybe_materialize_shared_index_buffer = fake_materialize
         indexer._get_topk_ragged_with_cp = fake_get_topk
 
+        class Mode:
+            def is_extend_without_speculative(self):
+                return True
+
         forward_batch = type(
             "ForwardBatchStub",
             (),
             {
+                "forward_mode": Mode(),
+                "extend_prefix_lens_cpu": [0],
+                "extend_seq_lens_cpu": [5],
+                "seq_lens_cpu": torch.tensor([5], dtype=torch.int64),
                 "nsa_cp_metadata": NSAContextParallelMetadata(
                     kv_len_prev=5,
                     kv_len_next=9,
@@ -741,10 +805,18 @@ class TestNSAInSeqCPUtils(unittest.TestCase):
         indexer._maybe_materialize_shared_index_buffer = fake_materialize
         indexer._get_topk_ragged_with_cp = fake_get_topk
 
+        class Mode:
+            def is_extend_without_speculative(self):
+                return True
+
         forward_batch = type(
             "ForwardBatchStub",
             (),
             {
+                "forward_mode": Mode(),
+                "extend_prefix_lens_cpu": [0],
+                "extend_seq_lens_cpu": [5],
+                "seq_lens_cpu": torch.tensor([5], dtype=torch.int64),
                 "nsa_cp_metadata": NSAContextParallelMetadata(
                     kv_len_prev=5,
                     kv_len_next=9,