[Bugfix][V1] Sync mamba_block_size via EngineCoreReadyResponse (#50809)

Signed-off-by: “新颐” <lxy537258@antgroup.com>
Co-authored-by: “新颐” <lxy537258@antgroup.com>
This commit is contained in:
lxy
2026-08-19 16:44:36 +00:00
committed by GitHub
co-authored by “新颐”
parent 3a386cfaf5
commit 0c8c3f41cf
4 changed files with 39 additions and 0 deletions
+1
View File
@@ -90,6 +90,7 @@ class EngineCoreReadyResponse:
instance_id: str
supports_lora: bool
max_loras: int
mamba_block_size: int | None = None
# KV cache capacity (None for encoder-only/attention-free models).
kv_cache_size_tokens: int | None = None
kv_cache_max_concurrency: float | None = None