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). @ dcb36de9c4faad5b5ff146f13bbf6fb73b228def

AlpinDale 5c3b94de45 spec decode: move ops.advane_step to flash attention backend (#1005)		2 meses atrás
..
__init__.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
cache_engine.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
cpu_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
cpu_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
embedding_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
enc_dec_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
model_runner_base.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
multi_step_model_runner.py	5c3b94de45 spec decode: move ops.advane_step to flash attention backend (#1005)	2 meses atrás
multi_step_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
neuron_model_runner.py	145e554a4d neuron: add 8bit quantization for Neuron (#994)	2 meses atrás
neuron_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
openvino_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
openvino_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
tpu_model_runner.py	0c56d23ece tpu: fix outputs by correcting the next_token_ids shape (#986)	2 meses atrás
tpu_worker.py	a50548c0b9 tpu: use XLA rank for persistent cache path (#989)	2 meses atrás
utils.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
worker_base.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
xpu_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás
xpu_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 meses atrás