djl-serving
djl-serving copied to clipboard
A universal scalable machine learning model deployment solution
Results
54
djl-serving issues
Sort by
recently updated
recently updated
newest added
## Description ## Update the tokenizer for benchmarks
## Description ## Remove engine from the settings
## Description ## Prepare dataset per guidance
## Description ## Per-token text is not supported. This may needs some changes on vllm/lmi_dist side. Per-token cum_logprob is not supported, but should be easy to add.