Keep CP HiCache draft KV invisible until joint readiness

CP HiCache now treats draft KV as a strict target-owned payload through pending write visibility, host eviction, and state-buffer registration. Host metadata created before async D2H ack is no longer request-visible, so match_prefix cannot select an in-flight host node. Draft host eviction now fails before target cleanup when draft metadata is missing, and prefill/decode share one helper for draft NSA state buffers so shared-KV mode cannot silently skip mismatched draft state.

Constraint: CP shared KV + HiCache + EAGLE/MTP must not expose target-only host hits or skipped draft state as valid cache hits

Rejected: Rely on event-loop ordering and lock_ref to hide in-flight writes | match_prefix does not consult lock_ref and can observe host_len/cp_hicache directly

Rejected: Keep draft state mismatch as debug-only skip | it can poison speculative acceptance while looking like a successful cache hit

Confidence: high

Scope-risk: moderate

Directive: Do not reintroduce silent draft/target fallback in CP shared-KV HiCache paths; malformed strong-sync metadata should fail fast

Tested: python -m py_compile targeted modified files

Tested: remote g0034 container pytest test/registered/unit/mem_cache/test_cp_hicache_metadata.py test/registered/unit/managers/test_hicache_controller_cp.py test/registered/unit/disaggregation/test_cp_shared_kv_transfer_mapping.py -q (91 passed)

Not-tested: Full CP shared KV + HiCache + EAGLE/MTP ETE server run after this commit
This commit is contained in:
laoyao0822
2026-05-27 05:46:34 +08:00
parent 71c4f66968
commit 367dff06f3
9 changed files with 448 additions and 42 deletions

View File

@@ -1,8 +1,11 @@
import unittest
from types import SimpleNamespace
from unittest.mock import patch
import numpy as np
from sglang.srt.disaggregation.utils import (
append_cp_draft_state_buffers,
filter_kv_pages_for_cp_shared_kv,
select_pages_by_request_positions,
)
@@ -56,6 +59,91 @@ class TestCPSharedKVTransferMapping(unittest.TestCase):
self.assertEqual(logical_positions.tolist(), [2, 6])
self.assertEqual(selected_decode_pages.tolist(), [43, 47])
def test_append_cp_draft_state_buffers_registers_nsa_state_as_target_payload(self):
kv_args = SimpleNamespace(
state_type="nsa",
state_data_ptrs=[11],
state_data_lens=[12],
state_item_lens=[13],
)
appended = append_cp_draft_state_buffers(
kv_args,
draft_state_type="nsa",
draft_state_data_ptrs=[21, 22],
draft_state_data_lens=[23, 24],
draft_state_item_lens=[25, 26],
role="prefill",
cp_rank=2,
)
self.assertTrue(appended)
self.assertEqual(kv_args.draft_state_type, "nsa")
self.assertEqual(kv_args.draft_state_buffer_start, 1)
self.assertEqual(kv_args.draft_state_buffer_count, 2)
self.assertEqual(kv_args.state_data_ptrs, [11, 21, 22])
self.assertEqual(kv_args.state_data_lens, [12, 23, 24])
self.assertEqual(kv_args.state_item_lens, [13, 25, 26])
def test_append_cp_draft_state_buffers_rejects_state_mismatch_under_shared_kv(self):
kv_args = SimpleNamespace(
state_type="nsa",
state_data_ptrs=[11],
state_data_lens=[12],
state_item_lens=[13],
)
with patch(
"sglang.srt.disaggregation.utils.envs.SGLANG_CP_DRAFT_SHARED_KV.get",
return_value=True,
):
with self.assertRaisesRegex(
RuntimeError,
"prefill.*cp_rank=2.*target_state_type=nsa.*draft_state_type=mamba",
):
append_cp_draft_state_buffers(
kv_args,
draft_state_type="mamba",
draft_state_data_ptrs=[21],
draft_state_data_lens=[22],
draft_state_item_lens=[23],
role="prefill",
cp_rank=2,
)
self.assertFalse(hasattr(kv_args, "draft_state_buffer_count"))
self.assertEqual(kv_args.state_data_ptrs, [11])
def test_append_cp_draft_state_buffers_keeps_legacy_skip_when_shared_kv_disabled(
self,
):
kv_args = SimpleNamespace(
state_type="nsa",
state_data_ptrs=[11],
state_data_lens=[12],
state_item_lens=[13],
)
with patch(
"sglang.srt.disaggregation.utils.envs.SGLANG_CP_DRAFT_SHARED_KV.get",
return_value=False,
):
appended = append_cp_draft_state_buffers(
kv_args,
draft_state_type="mamba",
draft_state_data_ptrs=[21],
draft_state_data_lens=[22],
draft_state_item_lens=[23],
role="decode",
cp_rank=3,
)
self.assertFalse(appended)
self.assertEqual(kv_args.draft_state_type, "mamba")
self.assertEqual(kv_args.draft_state_buffer_start, 1)
self.assertEqual(kv_args.draft_state_buffer_count, 0)
self.assertEqual(kv_args.state_data_ptrs, [11])
if __name__ == "__main__":
unittest.main()