[ModelRunnerV2][Hybrid model] Support kernel block size in hybrid model (#38831)

Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
Mengqing Cao
2026-05-28 00:55:55 +00:00
committed by GitHub
co-authored by Nick Hill
parent 381edde1b9
commit 1223732dda
5 changed files with 82 additions and 75 deletions
@@ -173,7 +173,7 @@ class EagleSpeculator:
) -> None:
self.model_state = model_state
self.kv_cache_config = kv_cache_config
_, self.attn_groups, _, _ = init_attn_backend(
self.attn_groups, _, _ = init_attn_backend(
kv_cache_config,
self.vllm_config,
self.device,