[Bugfix] Sync block_size from EngineCore to frontend for hybrid Mamba… (#42967)

Signed-off-by: Amit Gruner <agruner@crusoe.ai>
Co-authored-by: Amit Gruner <agruner@crusoe.ai>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
This commit is contained in:
gruner
2026-06-02 13:41:00 +00:00
committed by GitHub
co-authored by Amit Gruner Jiangyun Zhu
parent b623f7ea95
commit 654bd2bca4
4 changed files with 32 additions and 1 deletions
+1
View File
@@ -1462,6 +1462,7 @@ class EngineCoreProc(EngineCore):
ready_response = EngineCoreReadyResponse(
max_model_len=self.vllm_config.model_config.max_model_len,
num_gpu_blocks=self.vllm_config.cache_config.num_gpu_blocks or 0,
block_size=self.vllm_config.cache_config.block_size,
dp_stats_address=self.frontend_stats_publish_address,
dtype=str(self.vllm_config.model_config.dtype).removeprefix("torch."),
vllm_version=VLLM_VERSION,