[Spec Decode][MRV2] RecoverSSM for Qwen GDN and PLE short conv (PR #58863)

Intake of open upstream PR vllm-project/vllm#58863. Active only with
VLLM_USE_V2_MODEL_RUNNER=1; inert otherwise.

Speculative decoding on Gated DeltaNet snapshotted the full recurrent
state after every draft position and reserved one Mamba block per draft
position. On a 24 GB card that is reserved VRAM we never use, plus
per-step copy traffic.

RecoverSSM, the protocol Kimi-K3 KDA already uses, replaces this:
verify runs from a read-only checkpoint and stores a small per-token
replay record [correction (V), normalized key (K), gate (1)] in fp32;
commit replays only the accepted tokens and writes the recurrent state
once, plus the block-boundary state in align mode. The PLE dilated
short conv compacts its accepted window with the same plan.

Conflict in vllm/models/qwen4_exp/nvidia/mtp.py: our get_top_tokens()
work put LocalArgmaxMixin on Qwen4ExpMTP, the PR adds SupportsReplaySSM
to the same base list. Kept both.

Co-Authored-By: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
2026-09-29 13:39:09 +07:00
co-authored by Hinata
31 changed files with 2777 additions and 226 deletions
+1
View File
@@ -85,6 +85,7 @@ MambaStateShapes: TypeAlias = (
| tuple[tuple[int, int, int]]
| tuple[tuple[int, int], tuple[int, int]]
| tuple[tuple[int, int], tuple[int, int, int]]
| tuple[tuple[int, int], tuple[int, int, int], tuple[int, int, int]]
| tuple[
tuple[int, int],
tuple[int, int, int],