Skip to content

Actions: AlibabaPAI/llumnix

offline_inference

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
484 workflow runs
484 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Core] Support for Scheduling-defined Prefill-Decode Disaggregation feature
offline_inference #34: Pull request #15 synchronize by Xinyi-ECNU
October 8, 2024 09:34 1h 53m 11s pd_disagg
October 8, 2024 09:34 1h 53m 11s
[Misc][Simulator] Update vllm simulator backend
offline_inference #33: Pull request #42 synchronize by ZeldaHuang
October 8, 2024 09:10 1h 19m 37s simulator
October 8, 2024 09:10 1h 19m 37s
[Misc][Simulator] Update vllm simulator backend
offline_inference #32: Pull request #42 synchronize by ZeldaHuang
October 8, 2024 09:05 24m 51s simulator
October 8, 2024 09:05 24m 51s
[Misc] Ensure Llumlet main thread exits on Engine.Step errors
offline_inference #31: Pull request #38 synchronize by KuilongCui
October 8, 2024 08:57 46m 12s exception
October 8, 2024 08:57 46m 12s
[Core] Add back ray queue to put request output tokens back to the api server
offline_inference #30: Pull request #41 synchronize by KuilongCui
October 8, 2024 08:23 57m 32s rayqueue
October 8, 2024 08:23 57m 32s
[Misc] Ensure Llumlet main thread exits on Engine.Step errors
offline_inference #29: Pull request #38 synchronize by KuilongCui
October 8, 2024 07:55 51m 32s exception
October 8, 2024 07:55 51m 32s
[Misc] Ensure Llumlet main thread exits on Engine.Step errors
offline_inference #28: Pull request #38 synchronize by KuilongCui
October 8, 2024 07:41 12m 6s exception
October 8, 2024 07:41 12m 6s
[Core] Support for Scheduling-defined Prefill-Decode Disaggregation feature
offline_inference #27: Pull request #15 synchronize by Xinyi-ECNU
October 8, 2024 07:08 27m 35s pd_disagg
October 8, 2024 07:08 27m 35s
[Core] Add back ray queue to put request output tokens back to the api server
offline_inference #26: Pull request #41 synchronize by KuilongCui
October 8, 2024 03:14 2m 25s rayqueue
October 8, 2024 03:14 2m 25s
[Misc][Simulator] Update vllm simulator backend
offline_inference #25: Pull request #42 synchronize by ZeldaHuang
September 29, 2024 08:52 42m 12s simulator
September 29, 2024 08:52 42m 12s
[Fix] Migration correctness test (#43)
offline_inference #24: Commit f4a617c pushed by ZeldaHuang
September 27, 2024 10:14 42m 9s main
September 27, 2024 10:14 42m 9s
[Fix] Migration correctness test
offline_inference #23: Pull request #43 synchronize by ZeldaHuang
September 27, 2024 08:34 1h 21m 4s fix/test_migration
September 27, 2024 08:34 1h 21m 4s
[Fix] Migration correctness test
offline_inference #22: Pull request #43 synchronize by ZeldaHuang
September 27, 2024 08:31 3m 12s fix/test_migration
September 27, 2024 08:31 3m 12s
[Fix] Migration correctness test
offline_inference #21: Pull request #43 opened by ZeldaHuang
September 27, 2024 07:41 32m 18s fix/test_migration
September 27, 2024 07:41 32m 18s
[Misc][Simulator] Update vllm simulator backend
offline_inference #20: Pull request #42 synchronize by ZeldaHuang
September 25, 2024 13:44 7m 38s simulator
September 25, 2024 13:44 7m 38s
[Misc][Simulator] Update vllm simulator backend
offline_inference #19: Pull request #42 opened by ZeldaHuang
September 25, 2024 05:36 30m 14s simulator
September 25, 2024 05:36 30m 14s
[Core] Support for Scheduling-defined Prefill-Decode Disaggregation feature
offline_inference #18: Pull request #15 synchronize by Xinyi-ECNU
September 25, 2024 03:45 29m 35s pd_disagg
September 25, 2024 03:45 29m 35s
[Core] Support for Scheduling-defined Prefill-Decode Disaggregation feature
offline_inference #17: Pull request #15 synchronize by Xinyi-ECNU
September 24, 2024 13:11 21m 39s pd_disagg
September 24, 2024 13:11 21m 39s
[Core] Support for Scheduling-defined Prefill-Decode Disaggregation feature
offline_inference #16: Pull request #15 synchronize by Xinyi-ECNU
September 24, 2024 01:59 1h 43m 24s pd_disagg
September 24, 2024 01:59 1h 43m 24s
[Core] Add back ray queue to put request output tokens back to the api server
offline_inference #15: Pull request #41 synchronize by KuilongCui
September 21, 2024 07:26 35m 9s rayqueue
September 21, 2024 07:26 35m 9s
[Core] Add back ray queue to put request output tokens back to the api server
offline_inference #14: Pull request #41 synchronize by KuilongCui
September 20, 2024 08:46 31m 55s rayqueue
September 20, 2024 08:46 31m 55s
[Core] Add back ray queue to put request output tokens back to the api server
offline_inference #13: Pull request #41 synchronize by KuilongCui
September 20, 2024 08:31 14m 21s rayqueue
September 20, 2024 08:31 14m 21s
[Core] Add back ray queue to put request output tokens back to the api server
offline_inference #12: Pull request #41 synchronize by KuilongCui
September 20, 2024 07:37 1m 35s rayqueue
September 20, 2024 07:37 1m 35s
[Core] Add back ray queue to put request output tokens back to the api server
offline_inference #11: Pull request #41 opened by KuilongCui
September 20, 2024 05:14 39m 48s rayqueue
September 20, 2024 05:14 39m 48s
[CI] Add comprehensive testing: migration, e2e, and bench (#30)
offline_inference #10: Commit 91a6454 pushed by KuilongCui
September 19, 2024 07:30 7m 26s main
September 19, 2024 07:30 7m 26s
ProTip! You can narrow down the results and go further in time using created:<2024-09-19 or the other filters available.