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 5b0c11d190 support pipeline parallel pynccl groups		5 months ago
..
__init__.py	04b53d2db5 chore: add initializer files	1 year ago
cache_engine.py	50b7c13db0 refactor: attention selector (#552)	6 months ago
cpu_model_runner.py	f6250c5516 move dockerfiles to root; fix cpu build	5 months ago
cpu_worker.py	50b7c13db0 refactor: attention selector (#552)	6 months ago
embedding_model_runner.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	5 months ago
model_runner.py	5b0c11d190 support pipeline parallel pynccl groups	5 months ago
neuron_model_runner.py	35ae01d7ba refactor: attention metadata term	6 months ago
neuron_worker.py	fca911ee0a vLLM Upstream Sync (#526)	6 months ago
worker.py	eb2c5c77df feat: enforce the max possible seqlen	5 months ago
worker_base.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	5 months ago