[V1][Hybrid] Mamba Prefix Caching with align mode (#30877)
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com> Signed-off-by: Chen Zhang <zhangch99@outlook.com> Co-authored-by: Chen Zhang <zhangch99@outlook.com>
This commit is contained in:
co-authored by
Chen Zhang
parent
fec9da0af4
commit
5206e5e28c
@@ -56,6 +56,7 @@ class MambaBase(AttentionLayerBase):
|
||||
block_size=mamba_block_size,
|
||||
page_size_padded=page_size_padded,
|
||||
mamba_type=self.mamba_type,
|
||||
mamba_cache_mode=vllm_config.cache_config.mamba_cache_mode,
|
||||
num_speculative_blocks=(
|
||||
vllm_config.speculative_config.num_speculative_tokens
|
||||
if vllm_config.speculative_config
|
||||
|
||||
Reference in New Issue
Block a user