Skip to content

GitLab

Unverified Commit f31ff874 authored by Russell Bryant's avatar Russell Bryant Committed by GitHub
Browse files

[Core] Drop overly aggressive whisper assertion (#25408) 


Signed-off-by: default avatarRussell Bryant <rbryant@redhat.com>
parent d588cd24
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 4 deletions
vllm/v1/core/sched/scheduler.py
View file @ f31ff874
...@@ -463,10 +463,6 @@ class Scheduler(SchedulerInterface): ...@@ -463,10 +463,6 @@ class Scheduler(SchedulerInterface):
# always padded to the maximum length. If we support other # always padded to the maximum length. If we support other
# encoder-decoder models, this will need to be updated if we # encoder-decoder models, this will need to be updated if we
# want to only allocate what is needed. # want to only allocate what is needed.
assert ("whisper"
in self.vllm_config.model_config.model.lower()), (
"Whisper is the only supported "
"encoder-decoder model.")
num_encoder_tokens =\ num_encoder_tokens =\
self.scheduler_config.max_num_encoder_input_tokens self.scheduler_config.max_num_encoder_input_tokens
else: else:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment