| .. |
|
__init__.py
|
Add distributed model executor abstraction (#3191)
|
2024-03-11 11:03:45 -07:00 |
|
cpu_executor.py
|
[Core][Bugfix][Perf] Introduce MQLLMEngine to avoid asyncio OH (#8157)
|
2024-09-18 13:56:58 +00:00 |
|
distributed_gpu_executor.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
|
executor_base.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
|
gpu_executor.py
|
[misc] [doc] [frontend] LLM torch profiler support (#7943)
|
2024-09-06 17:48:48 -07:00 |
|
msgspec_utils.py
|
[Core] Optimize SPMD architecture with delta + serialization optimization (#7109)
|
2024-08-18 17:57:20 -07:00 |
|
multiproc_gpu_executor.py
|
[Core] Improve choice of Python multiprocessing method (#8823)
|
2024-09-29 09:17:07 +08:00 |
|
multiproc_worker_utils.py
|
[Core] Improve choice of Python multiprocessing method (#8823)
|
2024-09-29 09:17:07 +08:00 |
|
multiproc_xpu_executor.py
|
[Hardware][Intel GPU] Add intel GPU pipeline parallel support. (#7810)
|
2024-08-27 10:07:02 -07:00 |
|
neuron_executor.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
|
openvino_executor.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
|
ray_gpu_executor.py
|
[Misc] Limit to ray[adag] 2.35 to avoid backward incompatible change (#8509)
|
2024-09-17 00:06:26 -07:00 |
|
ray_tpu_executor.py
|
[BugFix] Fix clean shutdown issues (#8492)
|
2024-09-16 09:33:46 -07:00 |
|
ray_utils.py
|
[Bugfix] Ray 2.9.x doesn't expose available_resources_per_node (#8767)
|
2024-09-25 00:52:26 -07:00 |
|
ray_xpu_executor.py
|
[Hardware][Intel GPU] refactor xpu_model_runner for tp (#7712)
|
2024-08-22 20:06:54 -07:00 |
|
tpu_executor.py
|
[TPU] Implement multi-step scheduling (#8489)
|
2024-09-14 16:58:31 -07:00 |
|
xpu_executor.py
|
[Core] Logprobs support in Multi-step (#7652)
|
2024-08-29 19:19:08 -07:00 |
d1537039ce