Skip to content

Fix packed-QKV and broadcast-head bias strides in quantized GQA flash attention#28963

Open
tianleiwu wants to merge 5 commits into
mainfrom
tlwu/fix_gqa_quantized_kv
Open

Fix packed-QKV and broadcast-head bias strides in quantized GQA flash attention#28963
tianleiwu wants to merge 5 commits into
mainfrom
tlwu/fix_gqa_quantized_kv

Commits