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