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).

AlpinDale 6212072245 api: support LoRA lineage and base model metadata management (#1072)		4 days ago
..
__init__.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 weeks ago
cache_engine.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 weeks ago
cpu_model_runner.py	65a59bbb6b cpu: raise error if using encoder-decoder models (#1027)	1 week ago
cpu_worker.py	f2b6dc3872 cpu: add support for W8A8 quantization via compressed-tensor (#1017)	1 week ago
embedding_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 weeks ago
enc_dec_model_runner.py	314fa7f7d9 fix: encoder-decoder models for beam search (#1064)	5 days ago
model_runner.py	a985143768 core: add cuda graph support for encoder-decoder models (#1051)	1 week ago
model_runner_base.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	4 days ago
multi_step_model_runner.py	d9d287a288 rocm: enable multi-step scheduling for rocm (#1071)	4 days ago
multi_step_tpu_worker.py	4b1b658855 tpu: implement multi-step scheduling (#1046)	1 week ago
multi_step_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 weeks ago
neuron_model_runner.py	145e554a4d neuron: add 8bit quantization for Neuron (#994)	1 week ago
neuron_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 weeks ago
openvino_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 weeks ago
openvino_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 weeks ago
tpu_model_runner.py	4b1b658855 tpu: implement multi-step scheduling (#1046)	1 week ago
tpu_worker.py	a50548c0b9 tpu: use XLA rank for persistent cache path (#989)	2 weeks ago
utils.py	a985143768 core: add cuda graph support for encoder-decoder models (#1051)	1 week ago
worker.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	1 week ago
worker_base.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 weeks ago
xpu_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 weeks ago
xpu_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 weeks ago