ViperEkura b89f8436ea refactor: 将KV缓存槽位映射下沉到模型注意力层，移除_remap_kv和_writeback_kv

2026-05-06 20:01:22 +08:00

..

__init__.py

chore: 修改类名，优化导入顺序

2026-04-05 22:27:57 +08:00

automodel.py

chore: 修改类名，优化导入顺序

2026-04-05 22:27:57 +08:00

module.py

refactor: 将KV缓存槽位映射下沉到模型注意力层，移除_remap_kv和_writeback_kv

2026-05-06 20:01:22 +08:00

transformer.py

refactor: 将KV缓存槽位映射下沉到模型注意力层，移除_remap_kv和_writeback_kv

2026-05-06 20:01:22 +08:00