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). @ 9bbc75d2e3389428a587af92f60e94482898ae15

AlpinDale 5b0c11d190 support pipeline parallel pynccl groups		hace 6 meses
..
__init__.py	04b53d2db5 chore: add initializer files	hace 1 año
cache_engine.py	50b7c13db0 refactor: attention selector (#552)	hace 6 meses
cpu_model_runner.py	f6250c5516 move dockerfiles to root; fix cpu build	hace 6 meses
cpu_worker.py	50b7c13db0 refactor: attention selector (#552)	hace 6 meses
embedding_model_runner.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	hace 6 meses
model_runner.py	5b0c11d190 support pipeline parallel pynccl groups	hace 6 meses
neuron_model_runner.py	35ae01d7ba refactor: attention metadata term	hace 6 meses
neuron_worker.py	fca911ee0a vLLM Upstream Sync (#526)	hace 7 meses
worker.py	eb2c5c77df feat: enforce the max possible seqlen	hace 6 meses
worker_base.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	hace 6 meses