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). @ deepseek_v3

AlpinDale 1390915778 multi-step: add support for flashinfer attention backend (#1033)		4 tygodni temu
..
__init__.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	1 miesiąc temu
cache_engine.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	1 miesiąc temu
cpu_model_runner.py	65a59bbb6b cpu: raise error if using encoder-decoder models (#1027)	4 tygodni temu
cpu_worker.py	f2b6dc3872 cpu: add support for W8A8 quantization via compressed-tensor (#1017)	4 tygodni temu
embedding_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	1 miesiąc temu
enc_dec_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	1 miesiąc temu
model_runner.py	304e1e5a8a core: dump model runner inputs during crash (#1023)	4 tygodni temu
model_runner_base.py	304e1e5a8a core: dump model runner inputs during crash (#1023)	4 tygodni temu
multi_step_model_runner.py	1390915778 multi-step: add support for flashinfer attention backend (#1033)	4 tygodni temu
multi_step_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	1 miesiąc temu
neuron_model_runner.py	145e554a4d neuron: add 8bit quantization for Neuron (#994)	1 miesiąc temu
neuron_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	1 miesiąc temu
openvino_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	1 miesiąc temu
openvino_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	1 miesiąc temu
tpu_model_runner.py	0c56d23ece tpu: fix outputs by correcting the next_token_ids shape (#986)	1 miesiąc temu
tpu_worker.py	a50548c0b9 tpu: use XLA rank for persistent cache path (#989)	1 miesiąc temu
utils.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	1 miesiąc temu
worker.py	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	4 tygodni temu
worker_base.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	1 miesiąc temu
xpu_model_runner.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	1 miesiąc temu
xpu_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	1 miesiąc temu