Skip to content

Actions: InternLM/lmdeploy

publish-docker

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
841 workflow runs
841 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

refactor fused_moe on ascend platform (#2613)
publish-docker #767: Commit 77be205 pushed by lvhan028
October 21, 2024 03:03 30d 0h 0m 3s main
October 21, 2024 03:03 30d 0h 0m 3s
Add barrier to prevent TP nccl kernel waiting. (#2607)
publish-docker #766: Commit c918669 pushed by lvhan028
October 21, 2024 02:59 30d 0h 0m 3s main
October 21, 2024 02:59 30d 0h 0m 3s
set capture mode thread_local (#2560)
publish-docker #765: Commit a465e60 pushed by lvhan028
October 21, 2024 02:20 30d 0h 0m 3s main
October 21, 2024 02:20 30d 0h 0m 3s
refactor for multiple devices in dlinfer (#2619)
publish-docker #764: Commit e98ed5b pushed by lvhan028
October 18, 2024 09:16 30d 0h 0m 3s main
October 18, 2024 09:16 30d 0h 0m 3s
optimize paged attention on triton3 (#2553)
publish-docker #763: Commit 7dc0a5c pushed by lvhan028
October 18, 2024 04:31 30d 0h 0m 3s main
October 18, 2024 04:31 30d 0h 0m 3s
Add a workaround for saving internvl2 with latest transformers (#2583)
publish-docker #762: Commit fec94c9 pushed by lvhan028
October 17, 2024 07:22 30d 0h 0m 3s main
October 17, 2024 07:22 30d 0h 0m 3s
Support pytorch engine kv int4/int8 quantization (#2438)
publish-docker #761: Commit 4126067 pushed by lvhan028
October 14, 2024 12:40 30d 0h 0m 3s main
October 14, 2024 12:40 30d 0h 0m 3s
fix: make exit_flag verification for ascend more general (#2588)
publish-docker #760: Commit 88eccb2 pushed by lvhan028
October 14, 2024 03:36 30d 0h 0m 3s main
October 14, 2024 03:36 30d 0h 0m 3s
[Doc]: Lock sphinx version (#2594)
publish-docker #759: Commit 1d442df pushed by lvhan028
October 12, 2024 06:45 2h 44m 21s main
October 12, 2024 06:45 2h 44m 21s
Add instruction for downloading models from openmind hub (#2577)
publish-docker #758: Commit 64c5084 pushed by lvhan028
October 11, 2024 03:07 30d 0h 0m 3s main
October 11, 2024 03:07 30d 0h 0m 3s
update copyright (#2579)
publish-docker #757: Commit fd33b59 pushed by lvhan028
October 10, 2024 12:52 30d 0h 0m 2s main
October 10, 2024 12:52 30d 0h 0m 2s
Fix llama3.2-1b inference error by handling tie_word_embedding (#2568)
publish-docker #756: Commit 231e5bb pushed by lvhan028
October 9, 2024 11:23 30d 0h 0m 3s main
October 9, 2024 11:23 30d 0h 0m 3s
Add tool role for langchain usage (#2558)
publish-docker #755: Commit c722ff5 pushed by lvhan028
October 9, 2024 09:41 30d 0h 0m 3s main
October 9, 2024 09:41 30d 0h 0m 3s
add check for device with cap 7.x (#2535)
publish-docker #754: Commit 7c6b107 pushed by lvhan028
October 9, 2024 03:53 30d 0h 0m 2s main
October 9, 2024 03:53 30d 0h 0m 2s
support downloading models from openmind_hub (#2563)
publish-docker #753: Commit a5ee8df pushed by lvhan028
October 9, 2024 03:15 30d 0h 0m 2s main
October 9, 2024 03:15 30d 0h 0m 2s
set outlines<0.1.0 (#2559)
publish-docker #752: Commit 677207b pushed by lvhan028
October 9, 2024 02:55 30d 0h 0m 2s main
October 9, 2024 02:55 30d 0h 0m 2s
Add argument to disable FastAPI docs (#2540)
publish-docker #751: Commit 6f34738 pushed by lvhan028
October 8, 2024 11:33 30d 0h 0m 3s main
October 8, 2024 11:33 30d 0h 0m 3s
bump version to v0.6.1 (#2513)
publish-docker #750: Commit 2e49fc3 pushed by lvhan028
September 28, 2024 11:34 1h 12m 55s v0.6.1
September 28, 2024 11:34 1h 12m 55s
bump version to v0.6.1 (#2513)
publish-docker #749: Commit 2e49fc3 pushed by lvhan028
September 28, 2024 07:13 1h 2m 38s main
September 28, 2024 07:13 1h 2m 38s
fix vl gradio (#2527)
publish-docker #748: Commit 8db20bc pushed by lvhan028
September 27, 2024 12:11 30d 0h 0m 4s main
September 27, 2024 12:11 30d 0h 0m 4s
The get_ppl missed the last token of each iteration during multi-it…
publish-docker #747: Commit 4812b5a pushed by lvhan028
September 26, 2024 12:00 30d 0h 0m 3s main
September 26, 2024 12:00 30d 0h 0m 3s
Fix chatglm tokenizer failed when transformers>=4.45.0 (#2520)
publish-docker #746: Commit bb1dfa6 pushed by lvhan028
September 26, 2024 11:31 30d 0h 0m 3s main
September 26, 2024 11:31 30d 0h 0m 3s
refactor: optimize performance of ascend backend's update_step_contex…
publish-docker #745: Commit 0323103 pushed by lvhan028
September 26, 2024 09:30 30d 0h 0m 2s main
September 26, 2024 09:30 30d 0h 0m 2s
support noaligned silu_and_mul (#2506)
publish-docker #744: Commit 4bcfc18 pushed by lvhan028
September 25, 2024 09:06 30d 0h 0m 3s main
September 25, 2024 09:06 30d 0h 0m 3s
Catch exceptions thrown by turbomind inference thread (#2502)
publish-docker #743: Commit f012c86 pushed by lvhan028
September 24, 2024 13:56 30d 0h 0m 3s main
September 24, 2024 13:56 30d 0h 0m 3s