[Bugfix][Spec Decode] Cache the Mamba state at the block-grid position of EAGLE resume (#53945)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com> Signed-off-by: Adam Shaver <ashaver@nvidia.com> Signed-off-by: akshaver <168006157+akshaver@users.noreply.github.com> Co-authored-by: wzhao18 <wzhao18.sz@gmail.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> Co-authored-by: roikoren755 <26850796+roikoren755@users.noreply.github.com>
This commit is contained in:
co-authored by
wzhao18
Claude Opus 5
roikoren755
parent
414057a3d3
commit
263c4ff95f
@@ -195,6 +195,12 @@ class CacheConfig:
|
||||
when the token is at position i * block_size. This is the default when prefix
|
||||
caching is enabled.
|
||||
"""
|
||||
enable_mamba_fine_grained_prefix_cache: bool = False
|
||||
"""Also register a Mamba "align" checkpoint at the shared-prefix junction --
|
||||
where an EAGLE/MTP sibling was observed to resume -- instead of only at the
|
||||
prompt tail. Off by default; only takes effect with `mamba_cache_mode`
|
||||
"align", EAGLE on the Mamba group, and a prefix match unit smaller than the
|
||||
Mamba block size."""
|
||||
replayssm_buffer_len: int = Field(default=16, gt=0)
|
||||
"""ReplaySSM logical history length B for Mamba2. Triton uses B physical
|
||||
rows and FlashInfer uses B+1. Kimi-K3 speculative decode does not use B.
|
||||
@@ -274,6 +280,7 @@ class CacheConfig:
|
||||
"prefix_cache_retention_interval",
|
||||
# Prefix-caching implementation detail (doesn't affect compiled graph).
|
||||
"prefix_match_unit",
|
||||
"enable_mamba_fine_grained_prefix_cache",
|
||||
"mamba_page_size_padded",
|
||||
"skip_page_size_padded",
|
||||
"user_specified_block_size",
|
||||
|
||||
Reference in New Issue
Block a user