Skip to content

Added Causal Mask Pattern Fusion for LongRoPe Models and Cache Insertion for Phi4-mini-reasoning#2461

Draft
tadani3 wants to merge 12 commits intomicrosoft:mainfrom
tadani3:longrope_causal_mask
Draft

Added Causal Mask Pattern Fusion for LongRoPe Models and Cache Insertion for Phi4-mini-reasoning#2461
tadani3 wants to merge 12 commits intomicrosoft:mainfrom
tadani3:longrope_causal_mask