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