Files
xc-llm-ascend/vllm_ascend/worker
Tony b1557abab6 fix multistep bug,remove uselesscodes (#355)
1. remove useluss code in attention.py
2. multistep now using StatefulModelInputForNPU and do not use
StatefulModelInput

Signed-off-by: new-TonyWang <wangtonyyu222@gmail.com>
2025-03-28 09:55:35 +08:00
..
2025-03-04 15:59:34 +08:00