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). @ cuda_lora

AlpinDale 867939a6db bring back cuda kernels for lroa		3 bulan lalu
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	1 tahun lalu
block.py	7df7b8ca53 optimization: reduce end-to-end overhead from python obj allocation (#666)	4 bulan lalu
config.py	867939a6db bring back cuda kernels for lroa	3 bulan lalu
connections.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 bulan lalu
grammar.py	0527131e93 fix: grammar logits processor (#268)	10 bulan lalu
logger.py	867939a6db bring back cuda kernels for lroa	3 bulan lalu
logits_processor.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 bulan lalu
outputs.py	0e558e9b2f fix: loading chameleon model with TP>1 (#695)	4 bulan lalu
pooling_params.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 bulan lalu
sampling_params.py	ad181e3fef feat: bring back dynatemp (#754)	3 bulan lalu
sequence.py	577586309d chore: multi-step args and sequence modifications (#713)	3 bulan lalu
test_utils.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 bulan lalu
utils.py	0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712)	3 bulan lalu