AlpinDale f2b6dc3872 cpu: add support for W8A8 quantization via compressed-tensor (#1017) 2 周之前
..
__init__.py f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 9 月之前
cpu_executor.py f2b6dc3872 cpu: add support for W8A8 quantization via compressed-tensor (#1017) 2 周之前
distributed_gpu_executor.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
executor_base.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
gpu_executor.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 2 周之前
msgspec_utils.py 2f61644f6e SPMD optimizations (#824) 1 月之前
multiproc_gpu_executor.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
multiproc_worker_utils.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 2 周之前
multiproc_xpu_executor.py 15cb8d5c26 xpu: support pipeline parallel (#932) 2 周之前
neuron_executor.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 2 周之前
openvino_executor.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 2 周之前
ray_gpu_executor.py 4737c22ab3 fix: pass `APHRODITE_ATTENTION_BACKEND` to ray workers (#1009) 2 周之前
ray_tpu_executor.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 2 周之前
ray_utils.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 2 周之前
ray_xpu_executor.py 673621a3d2 xpu: refactor the model runner for tensor parallelism (#910) 3 周之前
tpu_executor.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 2 周之前
xpu_executor.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 2 周之前