Skip to content

[Core] More-efficient cross-attention parallel QKV computation#7448

Closed
afeldman-nm wants to merge 29 commits intovllm-project:mainfrom
neuralmagic:afeldman-nm/infra_enc_dec_cross2
Closed

[Core] More-efficient cross-attention parallel QKV computation#7448
afeldman-nm wants to merge 29 commits intovllm-project:mainfrom
neuralmagic:afeldman-nm/infra_enc_dec_cross2

Commits

Commits on Aug 11, 2024

Commits on Aug 12, 2024

Commits on Aug 13, 2024

Commits on Aug 16, 2024

Commits on Aug 20, 2024