-
Xin Li authored
Fix Flashinfer Allreduce+Norm enable disable calculation based on `fi_allreduce_fusion_max_token_num` (#21325) Signed-off-by:XIn Li <xinli@nvidia.com>
ae268b63
Fix Flashinfer Allreduce+Norm enable disable calculation based on `fi_allreduce_fusion_max_token_num` (#21325)
Signed-off-by:
XIn Li <xinli@nvidia.com>