Skip to content

Actions: InternLM/lmdeploy

unit-test

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
3,156 workflow runs
3,156 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Refactor VLM modules
unit-test #3133: Pull request #2810 synchronize by lvhan028
December 5, 2024 03:53 13m 51s refactor-vl
December 5, 2024 03:53 13m 51s
Refactor VLM modules
unit-test #3132: Pull request #2810 synchronize by lvhan028
December 4, 2024 13:25 13m 9s refactor-vl
December 4, 2024 13:25 13m 9s
convert kv cache to nd format in ascend graph mode (#2853)
unit-test #3131: Commit 9bfdeae pushed by lvhan028
December 4, 2024 11:48 12m 53s main
December 4, 2024 11:48 12m 53s
Refactor VLM modules
unit-test #3130: Pull request #2810 synchronize by grimoire
December 4, 2024 08:49 12m 41s refactor-vl
December 4, 2024 08:49 12m 41s
Refactor turbomind attention by precomputing rotary embed
unit-test #3129: Pull request #2801 synchronize by irexyc
December 4, 2024 08:37 14m 1s irexyc:rope
December 4, 2024 08:37 14m 1s
Refactor VLM modules
unit-test #3128: Pull request #2810 synchronize by grimoire
December 4, 2024 08:08 14m 32s refactor-vl
December 4, 2024 08:08 14m 32s
Supports W8A8 quantization for more models (#2850)
unit-test #3125: Commit 69a4306 pushed by lvhan028
December 4, 2024 05:39 12m 3s main
December 4, 2024 05:39 12m 3s
[ascend]feat: support kv int8
unit-test #3124: Pull request #2736 synchronize by jinminxi104
December 4, 2024 04:50 11m 55s DeepLink-org:ascend_kv_int8
December 4, 2024 04:50 11m 55s
[ascend]feat: support kv int8
unit-test #3123: Pull request #2736 synchronize by jinminxi104
December 4, 2024 04:47 12m 26s DeepLink-org:ascend_kv_int8
December 4, 2024 04:47 12m 26s
Refactor VLM modules
unit-test #3122: Pull request #2810 synchronize by lvhan028
December 4, 2024 04:14 12m 51s refactor-vl
December 4, 2024 04:14 12m 51s
[ascend]feat: support kv int8
unit-test #3121: Pull request #2736 synchronize by Reinerzhou
December 4, 2024 01:47 12m 23s DeepLink-org:ascend_kv_int8
December 4, 2024 01:47 12m 23s
[ascend]feat: support kv int8
unit-test #3120: Pull request #2736 synchronize by jinminxi104
December 3, 2024 16:27 12m 24s DeepLink-org:ascend_kv_int8
December 3, 2024 16:27 12m 24s
Refactor turbomind attention by precomputing rotary embed
unit-test #3119: Pull request #2801 synchronize by irexyc
December 3, 2024 12:58 12m 43s irexyc:rope
December 3, 2024 12:58 12m 43s
[maca] add env to support different mm layout on maca. (#2835)
unit-test #3118: Commit cc8cfb0 pushed by lvhan028
December 3, 2024 08:45 12m 57s main
December 3, 2024 08:45 12m 57s
[dlinfer] change dlinfer kv_cache layout and ajust paged_prefill_atte…
unit-test #3117: Commit a6645b2 pushed by lvhan028
December 3, 2024 08:44 12m 48s main
December 3, 2024 08:44 12m 48s
Refactor VLM modules
unit-test #3116: Pull request #2810 synchronize by grimoire
December 3, 2024 08:00 14m 25s refactor-vl
December 3, 2024 08:00 14m 25s
Supports W8A8 quantization for more models
unit-test #3115: Pull request #2850 opened by AllentDan
December 3, 2024 07:34 12m 29s AllentDan:w8a8-llm
December 3, 2024 07:34 12m 29s
Refactor turbomind attention by precomputing rotary embed
unit-test #3114: Pull request #2801 synchronize by irexyc
December 3, 2024 07:30 12m 32s irexyc:rope
December 3, 2024 07:30 12m 32s
check whether backend_config is None or not before accessing its attr…
unit-test #3113: Commit efa8ac0 pushed by lvhan028
December 3, 2024 06:46 13m 17s main
December 3, 2024 06:46 13m 17s
fix the logic to verify whether AutoAWQ has been successfully install…
unit-test #3112: Commit 0dedd73 pushed by lvhan028
December 3, 2024 06:44 12m 52s main
December 3, 2024 06:44 12m 52s
profile throughput without new threads (#2826)
unit-test #3110: Commit 8fbfed6 pushed by lvhan028
December 3, 2024 03:14 13m 20s main
December 3, 2024 03:14 13m 20s