Antoni Baum 50eed24d25 Add cuda_device_count_stateless (#5473)

2024-06-13 16:06:49 -07:00

..

__init__.py

Add distributed model executor abstraction (#3191)

2024-03-11 11:03:45 -07:00

cpu_executor.py

[Misc][Refactor] Introduce ExecuteModelData (#4540)

2024-05-03 17:47:07 -07:00

distributed_gpu_executor.py

[Core] Eliminate parallel worker per-step task scheduling overhead (#4894)

2024-05-23 06:17:27 +09:00

executor_base.py

[Core] Eliminate parallel worker per-step task scheduling overhead (#4894)

2024-05-23 06:17:27 +09:00

gpu_executor.py

[Speculative decoding][Re-take] Enable TP>1 speculative decoding (#4840)

2024-05-16 00:53:51 -07:00

multiproc_gpu_executor.py

Add cuda_device_count_stateless (#5473)

2024-06-13 16:06:49 -07:00

multiproc_worker_utils.py

[Core][Doc] Default to multiprocessing for single-node distributed case (#5230)

2024-06-11 11:10:41 -07:00

neuron_executor.py

[Misc][Refactor] Introduce ExecuteModelData (#4540)

2024-05-03 17:47:07 -07:00

ray_gpu_executor.py

Remove Ray health check (#4693)

2024-06-07 10:01:56 +00:00

ray_utils.py

[Core] Add MultiprocessingGPUExecutor (#4539)

2024-05-14 10:38:59 -07:00

tpu_executor.py

[Hardware] Initial TPU integration (#5292)

2024-06-12 11:53:03 -07:00