njaramish

## How to reproduce the behaviour ```python spacy.prefer_gpu() nlp = spacy.load( "en_core_web_trf", disable=['tagger', 'ner', 'lemmatizer', 'textcat'] ) node = """Some really long string, 3000 characters""" # simulating 96 pretty long...

**Description** When setting dynamic batching and a large batch size in `config.pbtxt` and submitting N individual inference requests, the Triton BLS model iterates through the N requests, executing batches of...