This product includes an Ascend adaptation of the TriAttention scoring method.

TriAttention
Copyright its contributors
Licensed under the Apache License, Version 2.0.
Source snapshot used for the adaptation:
https://github.com/WeianMao/triattention/tree/a4bc3c8f709db60f016ef42c3feb290fd0c00c1b

The implementation uses the provider-neutral KV-cache compression contracts
from vLLM-HUST and the out-of-tree platform conventions from
vLLM-Ascend-HUST. It does not copy the CUDA or Triton runtime kernels.

