PR #42329 [docs] Attention backends + continuous batching

[docs] Attention backends + continuous batching #42329

stevhliu merged 7 commits into huggingface:main from stevhliu:optimizations

stevhliu requested a review from

LysandreJik 123 days ago

stevhliu requested a review from

Cyrilvallez 123 days ago

stevhliu requested a review from

McPatate 123 days ago

McPatate commented on 2025-11-24

Cyrilvallez approved these changes on 2025-12-05

attention

da48413a

continuous batching

ffb1de5c

fix import

847bbef3

feedback

e1005e8b

link to blog post

ed4952cf

feedback

d1d3afc7

stevhliu force pushed from e783de5d to d1d3afc7 109 days ago

fix import

9634b085

stevhliu merged e3673ed4 into main 109 days ago

stevhliu deleted the optimizations branch 109 days ago

Reviewers

Cyrilvallez

McPatate

LysandreJik

Assignees

No one assigned

Labels

None yet

Milestone

No milestone