AlpinDale d44da0332c misc: rename `CudaMemoryProfiler` to `DeviceMemoryProfiler` (#1099) hai 1 mes
..
__init__.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) hai 2 meses
cache_engine.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) hai 2 meses
cpu_model_runner.py 65a59bbb6b cpu: raise error if using encoder-decoder models (#1027) hai 2 meses
cpu_worker.py f2b6dc3872 cpu: add support for W8A8 quantization via compressed-tensor (#1017) hai 2 meses
embedding_model_runner.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) hai 2 meses
enc_dec_model_runner.py 314fa7f7d9 fix: encoder-decoder models for beam search (#1064) hai 2 meses
model_runner.py d44da0332c misc: rename `CudaMemoryProfiler` to `DeviceMemoryProfiler` (#1099) hai 1 mes
model_runner_base.py 6212072245 api: support LoRA lineage and base model metadata management (#1072) hai 2 meses
multi_step_model_runner.py d9d287a288 rocm: enable multi-step scheduling for rocm (#1071) hai 2 meses
multi_step_tpu_worker.py 4b1b658855 tpu: implement multi-step scheduling (#1046) hai 2 meses
multi_step_worker.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) hai 2 meses
neuron_model_runner.py 145e554a4d neuron: add 8bit quantization for Neuron (#994) hai 2 meses
neuron_worker.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) hai 2 meses
openvino_model_runner.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) hai 2 meses
openvino_worker.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) hai 2 meses
tpu_model_runner.py 4b1b658855 tpu: implement multi-step scheduling (#1046) hai 2 meses
tpu_worker.py a50548c0b9 tpu: use XLA rank for persistent cache path (#989) hai 2 meses
utils.py a985143768 core: add cuda graph support for encoder-decoder models (#1051) hai 2 meses
worker.py a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019) hai 2 meses
worker_base.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) hai 2 meses
xpu_model_runner.py d44da0332c misc: rename `CudaMemoryProfiler` to `DeviceMemoryProfiler` (#1099) hai 1 mes
xpu_worker.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) hai 2 meses