[v0.9.1][Bugfix] Reset all unused positions to prevent out-of-bounds in GatherV3

[yiz-liu]

What this PR does / why we need it?

Reset all unused positions in NPUModelRunner to prevent out-of-bounds asserts in the GatherV3 operator.

Currently, in get_splitfuse_attn_mask, the position tensor may contain values that exceed the dimensions of the attention mask, triggering a GatherV3 boundary check failure. These invalid indices originate from stale “dirty” entries left over in position due to padding logic in the ACL graph. Specifically, in _process_reqs, the variable num_input_tokens is always greater than or equal to total_num_scheduled_tokens, so any positions not explicitly cleared from a previous batch will persist and cause this sporadic error.

BTW, in the original vLLM implementation, masks are constructed internally using other args, so these lingering values do not surface. However, on the Ascend platform—where split-fuse attention requires externally supplied masks—these residual indices become critical and lead to this elusive, hard-to-reproduce failure.

The fix is to explicitly reset or zero out all unused entries in the position tensor before passing it to GatherV3, ensuring that every index lies within the valid range of the attention mask.

Does this PR introduce any user-facing change?

How was this patch tested?

[yiz-liu]

This pull request addresses the following issues:
#1324 , #1115 , #1038

[Yikun]

Please also submit the PR to main

[ApsarasX]

LGTM