[None][fix] Guard transceiver session short-circuit against ADP+PP consensus deadlock

The sticky-role short-circuits in KvCacheTransceiverV2.check_context_transfer_status
and check_gen_transfer_status (sticky markers from #14042) returned early when a
transceiver had never opened a send/recv session, to skip the per-iter consensus
allgather on pure-role transceivers.

Under pipeline parallelism (and ADP request sharding) the per-rank
_ever_had_send_session / _ever_had_recv_session markers flip asymmetrically across
PP stages, so some ranks short-circuited and skipped the _ctx_consensus pp_allgather
barrier while peers entered it, deadlocking the collective. This was observed as a
hang in tests/unittest/disaggregated/test_cache_transceiver_single_process.py
::test_cache_transceiver[*-tp4_pp2_dp_both] (8-rank ADP+PP2).

Guard the short-circuit with `not self._ctx_need_pp_sync` (pp_size == 1) so it only
fires when there is no cross-stage consensus barrier: preserves the pure-role
tp_allgather-skip optimization for PP=1 while doing the full symmetric consensus
whenever pipeline parallelism is enabled.

Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>

Author: Shixiaowei02

tensorrt_llm/_torch/disaggregation/transceiver.py

@@ -470,8 +470,12 @@ def request_and_receive_async(self, req: LlmRequest):
     def check_context_transfer_status(
         self, at_least_request_num: Optional[int], mark_complete: bool = False
     ):
-        # Skip the tp_allgather in _ctx_consensus when this transceiver never sends (pure GEN role).
-        if not self._ever_had_send_session:
+        # Skip the consensus collectives when this transceiver never sends (pure GEN role).
+        # Guarded with pp_size==1 (not _ctx_need_pp_sync): under pipeline parallelism the
+        # per-rank send marker flips asymmetrically across PP stages, so short-circuiting here
+        # would let some ranks skip the pp_allgather barrier while peers enter it -> deadlock
+        # (e.g. ADP+PP tp4_pp2_dp_both). With PP=1 there is no cross-stage consensus barrier.
+        if not self._ever_had_send_session and not self._ctx_need_pp_sync:
             return [], []
         block_all = at_least_request_num is None
         wait_num = at_least_request_num if not block_all else 0
@@ -526,8 +530,11 @@ def check_context_transfer_status(
         return completed, failed
 
     def check_gen_transfer_status(self, at_least_request_num: Optional[int]):
-        # Skip the allgather in _gen_consensus when this transceiver never receives (pure CTX role).
-        if not self._ever_had_recv_session:
+        # Skip the consensus collectives when this transceiver never receives (pure CTX role).
+        # Guarded with pp_size==1 (not _ctx_need_pp_sync): see check_context_transfer_status --
+        # under PP the per-rank recv marker flips asymmetrically across stages, so an early
+        # return would desync the consensus barrier; only short-circuit when PP is absent.
+        if not self._ever_had_recv_session and not self._ctx_need_pp_sync:
             return [], [], []
         block_all = at_least_request_num is None
         wait_num = at_least_request_num if not block_all else 0