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). @ 737f1c3351c3d3824617efcc95550449e6a5fe18

AlpinDale 737f1c3351 part 1		7 mesi fa
..
fused_moe	46159b107a formatting: pt1	7 mesi fa
ops	fca911ee0a vLLM Upstream Sync (#526)	7 mesi fa
__init__.py	07aa2a492f upstream: add option to specify tokenizer	1 anno fa
activation.py	fca911ee0a vLLM Upstream Sync (#526)	7 mesi fa
layernorm.py	e31c6f0b45 feat: refactor modeling logic and support more models (#274)	11 mesi fa
linear.py	fca911ee0a vLLM Upstream Sync (#526)	7 mesi fa
logits_processor.py	737f1c3351 part 1	7 mesi fa
rejection.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 mesi fa
rotary_embedding.py	e7b1368156 feat: Phi3 support	7 mesi fa
sampler.py	fca911ee0a vLLM Upstream Sync (#526)	7 mesi fa
vocab_parallel_embedding.py	fca911ee0a vLLM Upstream Sync (#526)	7 mesi fa