### What this PR does / why we need it? Corrects attention metadata size for MTP when both asynchronous scheduling and full ACL graph mode are enabled. This prevents potential size mismatches during execution. Additionally, improves the robustness of calculating token sample indices by explicitly aligning tensor shapes. Finally, prevents padding when the number of input tokens exceeds the maximum ACL graph batch size to avoid out-of-bounds errors. ### Does this PR introduce _any_ user-facing change? None. ### How was this patch tested? Need to add corresponding test case ASAP. - vLLM version: v0.12.0 - vLLM main: https://github.com/vllm-project/vllm/commit/ad32e3e19ccf0526cb6744a5fed09a138a5fb2f9 --------- Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com> Signed-off-by: Yizhou <136800916+yiz-liu@users.noreply.github.com> Co-authored-by: Jade Zheng <zheng.shoujian@outlook.com>