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). @ feat/tree-attention

AlpinDale 60ca1e1e5e feat: add ngram prompt lookup decoding for speculative decoding (#438)		преди 9 месеца
..
__init__.py	df7ae8ce01 fix spec_decode and block imports	преди 9 месеца
batch_expansion.py	60ca1e1e5e feat: add ngram prompt lookup decoding for speculative decoding (#438)	преди 9 месеца
interfaces.py	d8c4193704 feat: Speculative Decoding using a draft model (#432)	преди 9 месеца
metrics.py	d8c4193704 feat: Speculative Decoding using a draft model (#432)	преди 9 месеца
multi_step_worker.py	60ca1e1e5e feat: add ngram prompt lookup decoding for speculative decoding (#438)	преди 9 месеца
ngram_worker.py	60ca1e1e5e feat: add ngram prompt lookup decoding for speculative decoding (#438)	преди 9 месеца
spec_decode_worker.py	60ca1e1e5e feat: add ngram prompt lookup decoding for speculative decoding (#438)	преди 9 месеца
top1_proposer.py	60ca1e1e5e feat: add ngram prompt lookup decoding for speculative decoding (#438)	преди 9 месеца
util.py	60ca1e1e5e feat: add ngram prompt lookup decoding for speculative decoding (#438)	преди 9 месеца