transformers
[serving] Fix continuous batching JSON response serialization
#45057
Merged

[serving] Fix continuous batching JSON response serialization #45057

NathanHB
NathanHB Fix continuous batching JSON response serialization
b126ffdc
LysandreJik
LysandreJik commented on 2026-03-27
NathanHB add example script eval-job
1a9bee08
HuggingFaceDocBuilderDev
NathanHB fix script
5ee9fcff
NathanHB Add test for continuous batching non-streaming JSON response
f86120cc
NathanHB
NathanHB fix ci
92899701
NathanHB Update eval script to use official transformers repo main branch
5fddeb2a
ArthurZucker
ArthurZucker approved these changes on 2026-03-30
NathanHB NathanHB force pushed from ec55108e to 5fddeb2a 6 days ago
github-actions
NathanHB add kernels and flash attn 2
db4a7746
NathanHB Add continuous batching configuration CLI arguments to serve command
e5fd8cc0
remi-or Add thread lock for manager creation to avoid double manager
f9729fa6
LysandreJik
LysandreJik approved these changes on 2026-03-31
NathanHB change transformers dep
9f7e1841
NathanHB NathanHB enabled auto-merge 5 days ago
NathanHB NathanHB merged a91232af into main 5 days ago
NathanHB NathanHB deleted the fix-continuous-batching-json-response branch 5 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone