Skip to content

Fix ROCm Q8->F16 cache reserve starving session tensors on large models (q4q2)#446

Open
alantsev wants to merge 1 commit into
antirez:mainfrom
alantsev:rocm-q4q2-oom
Open

Fix ROCm Q8->F16 cache reserve starving session tensors on large models (q4q2)#446
alantsev wants to merge 1 commit into
antirez:mainfrom
alantsev:rocm-q4q2-oom

Commits