david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention).

AlpinDale 6212072245 api: support LoRA lineage and base model metadata management (#1072)		6 dagar sedan
..
tool_parsers	a56bce4c94 fix: remove duplicate assignment in Hermes2ProToolParser	1 vecka sedan
__init__.py	07aa2a492f upstream: add option to specify tokenizer	1 år sedan
api_server.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	6 dagar sedan
args.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	6 dagar sedan
logits_processors.py	62111fab17 feat: allow serving encoder-decoder models in the API server (#664)	4 månader sedan
protocol.py	055c8905a3 api: add sampling/engine option to return only deltas or final output (#1035)	1 vecka sedan
run_batch.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	6 dagar sedan
samplers.json	ac82b67f75 feat: naive context shift and various QoL changes (#289)	10 månader sedan
serving_chat.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	6 dagar sedan
serving_completions.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	6 dagar sedan
serving_embedding.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	6 dagar sedan
serving_engine.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	6 dagar sedan
serving_tokenization.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	6 dagar sedan