[Core] structured generation mode for DiffusionGemma model (Jev-like) (#57250)
Signed-off-by: Matt Mastracci <matthew@mastracci.com> Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com> Signed-off-by: Razorback16 <razorback16@protonmail.com> Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com> Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by: Codex <noreply@openai.com> Co-authored-by: Razorback16 <razorback16@protonmail.com>
This commit is contained in:
co-authored by
Claude Fable 5.1
Lucas Wilkinson
Codex
Razorback16
parent
fae5cbfc8b
commit
1b3b88ec2b
@@ -1894,6 +1894,16 @@ class VllmConfig:
|
||||
)
|
||||
current_platform.check_and_update_config(self)
|
||||
|
||||
# After the platform hook, which has the last word on async scheduling.
|
||||
if (
|
||||
self.diffusion_config is not None
|
||||
and self.scheduler_config.async_scheduling
|
||||
and self.scheduler_config.scheduler_cls is None
|
||||
):
|
||||
self.scheduler_config.scheduler_cls = (
|
||||
"vllm.v1.core.sched.diffusion_scheduler.DiffusionAsyncScheduler"
|
||||
)
|
||||
|
||||
self._normalize_piecewise_cudagraph_mode(
|
||||
breakable_cudagraph_enabled=breakable_cudagraph_enabled
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user