fix(rpa-v3): add sliding window mask to h64 kernel and attention_sink to h128#1185
Open
erfanzar wants to merge 1 commit intovllm-project:mainfrom
Open
fix(rpa-v3): add sliding window mask to h64 kernel and attention_sink to h128#1185erfanzar wants to merge 1 commit intovllm-project:mainfrom
erfanzar wants to merge 1 commit intovllm-project:mainfrom