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). @ ae04f57ec148676c34c50834c735a59ca662a6e0

AlpinDale ae04f57ec1 feat: Pipeline Parallel support (#581)		7 bulan lalu
..
__init__.py	04b53d2db5 chore: add initializer files	1 tahun lalu
cache_engine.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	7 bulan lalu
cpu_model_runner.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	7 bulan lalu
cpu_worker.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	7 bulan lalu
embedding_model_runner.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	7 bulan lalu
model_runner.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	7 bulan lalu
model_runner_base.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	7 bulan lalu
neuron_model_runner.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	7 bulan lalu
neuron_worker.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	7 bulan lalu
openvino_model_runner.py	0886c361f4 feat: OpenVINO CPU backend (#576)	7 bulan lalu
openvino_worker.py	0886c361f4 feat: OpenVINO CPU backend (#576)	7 bulan lalu
tpu_model_runner.py	301ec7c77d fix: pad slot id in tpu runner	7 bulan lalu
tpu_worker.py	d0ff3fd59e fix: tpu sampler output	7 bulan lalu
worker.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	7 bulan lalu
worker_base.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	7 bulan lalu
xpu_model_runner.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	7 bulan lalu
xpu_worker.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	7 bulan lalu