Files
xc-llm-ascend/tests/ut/worker
pichangping 50e7934415 MLA prefill preformance optimization (#5456)
### What this PR does / why we need it?
Since the _npu_ring_mla operator deteriorates in long-sequencescenarios,
the long sequence is split into shorter sequences for input to improve
performance.

- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/5326c89803566a131c928f7fdd2100b75c981a42

---------

Signed-off-by: pichangping <1337510399@qq.com>
2026-01-05 11:41:59 +08:00
..