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). @ 84163654f47ff1c436eb297d2db68e70bf8d86a4

AlpinDale a985143768 core: add cuda graph support for encoder-decoder models (#1051)		hace 2 semanas
..
__init__.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	hace 2 semanas
cache_engine.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	hace 2 semanas
cpu_model_runner.py	65a59bbb6b cpu: raise error if using encoder-decoder models (#1027)	hace 2 semanas
cpu_worker.py	f2b6dc3872 cpu: add support for W8A8 quantization via compressed-tensor (#1017)	hace 2 semanas
embedding_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	hace 2 semanas
enc_dec_model_runner.py	a985143768 core: add cuda graph support for encoder-decoder models (#1051)	hace 2 semanas
model_runner.py	a985143768 core: add cuda graph support for encoder-decoder models (#1051)	hace 2 semanas
model_runner_base.py	304e1e5a8a core: dump model runner inputs during crash (#1023)	hace 2 semanas
multi_step_model_runner.py	1390915778 multi-step: add support for flashinfer attention backend (#1033)	hace 2 semanas
multi_step_tpu_worker.py	4b1b658855 tpu: implement multi-step scheduling (#1046)	hace 2 semanas
multi_step_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	hace 2 semanas
neuron_model_runner.py	145e554a4d neuron: add 8bit quantization for Neuron (#994)	hace 2 semanas
neuron_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	hace 2 semanas
openvino_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	hace 2 semanas
openvino_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	hace 2 semanas
tpu_model_runner.py	4b1b658855 tpu: implement multi-step scheduling (#1046)	hace 2 semanas
tpu_worker.py	a50548c0b9 tpu: use XLA rank for persistent cache path (#989)	hace 2 semanas
utils.py	a985143768 core: add cuda graph support for encoder-decoder models (#1051)	hace 2 semanas
worker.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	hace 2 semanas
worker_base.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	hace 2 semanas
xpu_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	hace 2 semanas
xpu_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	hace 2 semanas