Skip to content

[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support)#4942

Merged
robertgshaw2-redhat merged 624 commits intovllm-project:mainfrom neuralmagic:afeldman-nm/infra_enc_dec_model_runnerAug 6, 2024

Commits

This pull request is big! We're only showing the most recent 250 commits

Commits on Jul 15, 2024

Commits on Jul 17, 2024

Commits on Jul 20, 2024

Commits on Jul 22, 2024

Commits on Jul 25, 2024

Commits on Jul 26, 2024

Commits on Jul 31, 2024

Commits on Aug 3, 2024

Commits on Aug 5, 2024

Commits on Aug 6, 2024