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). @ 156f577f79c2751cabc9b823696ace6d029371d7

AlpinDale ec5b99d075 fix: use named args		7 months ago
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	10 months ago
batch_expansion.py	e0886ee929 feat: add `ProposerWorkerBase` abstract class	7 months ago
interfaces.py	e0886ee929 feat: add `ProposerWorkerBase` abstract class	7 months ago
metrics.py	9d81716bfd [v0.5.3] Release Candidate (#388)	10 months ago
multi_step_worker.py	e0886ee929 feat: add `ProposerWorkerBase` abstract class	7 months ago
ngram_worker.py	e0886ee929 feat: add `ProposerWorkerBase` abstract class	7 months ago
proposer_worker_base.py	ec5b99d075 fix: use named args	7 months ago
spec_decode_worker.py	e0886ee929 feat: add `ProposerWorkerBase` abstract class	7 months ago
top1_proposer.py	e0886ee929 feat: add `ProposerWorkerBase` abstract class	7 months ago
util.py	5b0c11d190 support pipeline parallel pynccl groups	7 months ago