[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
+2 -2
View File
@@ -151,7 +151,7 @@ def test_kda_recoverssm_derivation_is_revalidated():
config = SimpleNamespace(
cache_config=SimpleNamespace(
use_replayssm=True,
use_kda_recoverssm=False,
use_recoverssm=False,
mamba_cache_mode="none",
),
num_speculative_tokens=3,
@@ -170,7 +170,7 @@ def test_kda_recoverssm_derivation_is_revalidated():
VllmConfig.validate_mamba_cached_kernel(config)
assert config.cache_config.use_replayssm
assert config.cache_config.use_kda_recoverssm
assert config.cache_config.use_recoverssm
config.cache_config.mamba_cache_mode = "align"
VllmConfig.validate_mamba_cached_kernel(config)