| .. |
|
__init__.py
|
Add distributed model executor abstraction (#3191)
|
2024-03-11 11:03:45 -07:00 |
|
cpu_executor.py
|
[Core] Consolidate GB constant and enable float GB arguments (#7416)
|
2024-08-12 14:14:14 -07:00 |
|
distributed_gpu_executor.py
|
[Core] Introduce SPMD worker execution using Ray accelerated DAG (#6032)
|
2024-07-17 22:27:09 -07:00 |
|
executor_base.py
|
[Core] Add span metrics for model_forward, scheduler and sampler time (#7089)
|
2024-08-09 13:55:13 -07:00 |
|
gpu_executor.py
|
[Core] Add span metrics for model_forward, scheduler and sampler time (#7089)
|
2024-08-09 13:55:13 -07:00 |
|
multiproc_gpu_executor.py
|
[cuda][misc] remove error_on_invalid_device_count_status (#7069)
|
2024-08-02 00:14:21 -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
|
[Bugfix] update neuron for version > 0.5.0 (#7175)
|
2024-08-15 09:44:14 -07:00 |
|
openvino_executor.py
|
[Core] Consolidate GB constant and enable float GB arguments (#7416)
|
2024-08-12 14:14:14 -07:00 |
|
ray_gpu_executor.py
|
[Core] Shut down aDAG workers with clean async llm engine exit (#7224)
|
2024-08-12 17:57:16 -07:00 |
|
ray_tpu_executor.py
|
[Hardware][TPU] Implement tensor parallelism with Ray (#5871)
|
2024-07-26 20:54:27 -07:00 |
|
ray_utils.py
|
[hardware] unify usage of is_tpu to current_platform.is_tpu() (#7102)
|
2024-08-13 00:16:42 -07:00 |
|
ray_xpu_executor.py
|
[Core] Allow specifying custom Executor (#6557)
|
2024-07-20 01:25:06 +00:00 |
|
tpu_executor.py
|
[Core] Allow specifying custom Executor (#6557)
|
2024-07-20 01:25:06 +00:00 |
|
xpu_executor.py
|
[Core] Allow specifying custom Executor (#6557)
|
2024-07-20 01:25:06 +00:00 |
9c1f78d5d6