transformers
Run Qwen4-Exp under continuous batching
#50359
Open

Run Qwen4-Exp under continuous batching #50359

qgallouedec wants to merge 4 commits into cb-cache-layout from cb-indexed-attention
qgallouedec
qgallouedec WIP indexed attention and Qwen4-Exp under the engine
b9bd4fd5
qgallouedec Merge branch 'cb-cache-layout' into cb-indexed-attention
8a373081
qgallouedec Run Qwen4-Exp under continuous batching: indexed attention and per-la…
d75219d9
HuggingFaceDocBuilderDev
qgallouedec Merge branch 'cb-cache-layout' into cb-indexed-attention
77d19134
github-actions

Login to write a write a comment.

Login via GitHub

Reviewers
No reviews
Assignees
No one assigned
Labels
Milestone