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). @ bnb_tp

AlpinDale 6154031a85 feat: add TP support for bitsandbytes		3 hónapja
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	1 éve
block.py	7df7b8ca53 optimization: reduce end-to-end overhead from python obj allocation (#666)	4 hónapja
config.py	6154031a85 feat: add TP support for bitsandbytes	3 hónapja
connections.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 hónapja
grammar.py	8a71788372 Add OLMoE (#772)	3 hónapja
logger.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 hónapja
logits_processor.py	8a71788372 Add OLMoE (#772)	3 hónapja
outputs.py	0e558e9b2f fix: loading chameleon model with TP>1 (#695)	4 hónapja
pooling_params.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 hónapja
sampling_params.py	ad181e3fef feat: bring back dynatemp (#754)	4 hónapja
sequence.py	577586309d chore: multi-step args and sequence modifications (#713)	4 hónapja
test_utils.py	8a71788372 Add OLMoE (#772)	3 hónapja
utils.py	0256ed236b feat: windows support (#790)	3 hónapja