[Kernel] ReplaySSM: cache SSM inputs for faster Mamba2 standard decode (#48018)

Signed-off-by: Johnny-Liou <a897111@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: tomeras91 <57313761+tomeras91@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Johnny-Liou
2026-07-24 09:39:49 -07:00
committed by GitHub
co-authored by Claude Opus 4.8 mergify[bot] <37929162+mergify[bot]@users.noreply.github.com> tomeras91 Cyrus Leung
parent d02df748bf
commit 866fea2b99
23 changed files with 2954 additions and 31 deletions
+4
View File
@@ -1696,6 +1696,10 @@ class ModelConfig:
def supports_mamba_prefix_caching(self) -> bool:
return self._model_info.supports_mamba_prefix_caching
@property
def supports_replayssm(self) -> bool:
return self._model_info.supports_replayssm
@property
def use_mla(self) -> bool:
return self.is_deepseek_mla and not envs.VLLM_MLA_DISABLE