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). @ bitnet

AlpinDale 344ddaac5a properly disable speculative decoding		5 mesi fa
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 mesi fa
batch_expansion.py	a94de94c44 refactor: combine the prefill and decode into a single API (#553)	5 mesi fa
interfaces.py	ef733aee43 implement ExecuteModelData to reduce executor complexity	5 mesi fa
metrics.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 mesi fa
multi_step_worker.py	a94de94c44 refactor: combine the prefill and decode into a single API (#553)	5 mesi fa
ngram_worker.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	5 mesi fa
spec_decode_worker.py	344ddaac5a properly disable speculative decoding	5 mesi fa
top1_proposer.py	e42d0b3455 possibly improve ngram efficiency	5 mesi fa
util.py	5b0c11d190 support pipeline parallel pynccl groups	5 mesi fa