..
__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
[BugFix] Fix clean shutdown issues ( #8492 )
2024-09-16 09:33:46 -07:00
multiproc_worker_utils.py
[Core][Bugfix][Perf] Introduce MQLLMEngine to avoid asyncio OH ( #8157 )
2024-09-18 13:56:58 +00:00
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
[TPU] Support single and multi-host TPUs on GKE ( #7613 )
2024-08-30 00:27:40 -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