AMOOOMA commented on code in PR #40908:
URL: https://github.com/apache/beam/pull/40908#discussion_r4566549969
##########
sdks/python/apache_beam/ml/inference/vllm_inference.py:
##########
@@ -425,15 +465,31 @@ def __init__(
batch_bucket_boundaries: optional. a sorted list of positive boundary
values for length-aware batching buckets. Cannot be used together with
max_batch_weight.
+ prefix_batching_config: optional :class:`PrefixBatchingConfig`. When set,
+ prompts sharing a leading prefix are routed to the same worker and
+ batched together to maximize vLLM prefix cache hits (see
+ ``apache_beam.ml.inference.prefix_batching``).
+ enable_autoscaling_metric: if True (default), publish the
+ ``num_loaded_models_<tag>`` worker capacity signal from vLLM's request
+ metrics so Dataflow's GPU autoscaler scales workers with load. Requires
+ ``RunInference(..., use_model_manager=False)`` (the default); not
Review Comment:
Makes sense! More robust warning/error is better, sending a child PR after
this.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
