You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Describe the bug
The nlp_si_detection pipeline example prints the following warning message about a slow edge. The culprit appears to be the SerializeStage
W20220623 15:41:12.778241 2000453 node.hpp:271] WARNING: A slow edge connection between C++ nodes '[with T = std::shared_ptr<morpheus::MultiResponseProbsMessage>]' and '[with T = std::shared_ptr<morpheus::MultiMessage>]' has been detected. Performance between these nodes can be improved by registering an EdgeConverter at compile time. Without this, conversion to an intermediate python type will be necessary (i.e. C++ -> Python -> C++).
Steps/Code to reproduce bug
morpheus --log_level=DEBUG \
`# Run a pipeline with 8 threads and a model batch size of 32 (Must match Triton config)` \
run --num_threads=8 --pipeline_batch_size=1024 --model_max_batch_size=32 \
`# Specify a NLP pipeline with 256 sequence length (Must match Triton config)` \
pipeline-nlp --model_seq_length=256 \
`# 1st Stage: Read from file` \
from-file --filename=$MORPHEUS_ROOT/examples/data/pcap_dump.jsonlines \
`# 2nd Stage: Deserialize from JSON strings to objects` \
deserialize \
`# 3rd Stage: Preprocessing converts the input data into BERT tokens` \
preprocess --vocab_hash_file=$MORPHEUS_ROOT/morpheus/data/bert-base-uncased-hash.txt --do_lower_case=True --truncation=True \
`# 4th Stage: Send messages to Triton for inference. Specify the model loaded in Setup` \
inf-triton --model_name=sid-minibert-onnx --server_url=localhost:8000 --force_convert_inputs=True \
`# 5th Stage: Monitor stage prints throughput information to the console` \
monitor --description "Inference Rate" --smoothing=0.001 --unit inf \
`# 6th Stage: Add results from inference to the messages` \
add-class \
`# 7th Stage: Filtering removes any messages that did not detect SI` \
filter \
`# 8th Stage: Convert from objects back into strings` \
serialize --exclude '^_ts_' \
`# 9th Stage: A second Monitor stage to monitor the back-half of the pipeline` \
monitor --description "Serialize Rate" --smoothing=0.001 \
`# 10th Stage: Write out the JSON lines to the detections.jsonlines file` \
to-file --filename=detections.jsonlines --overwrite
Expected behavior
No warnings
Environment overview (please complete the following information)
Environment location: Bare-metal
Method of Morpheus install: from source
The text was updated successfully, but these errors were encountered:
Describe the bug
The
nlp_si_detection
pipeline example prints the following warning message about a slow edge. The culprit appears to be theSerializeStage
Steps/Code to reproduce bug
Expected behavior
No warnings
Environment overview (please complete the following information)
The text was updated successfully, but these errors were encountered: