Skip to content

Actions: InternLM/lmdeploy

publish-docker

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
797 workflow runs
797 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add non-stream inference api for chatbot (#200)
publish-docker #22: Commit 3de0dbb pushed by lvhan028
August 7, 2023 10:26 30d 0h 0m 3s main
August 7, 2023 10:26 30d 0h 0m 3s
[Feature] Add script to split HuggingFace model to the smallest shard…
publish-docker #21: Commit b7e7e66 pushed by lvhan028
August 7, 2023 04:49 30d 0h 0m 3s main
August 7, 2023 04:49 30d 0h 0m 3s
Improve postprocessing in TIS serving by applying Incremental de-toke…
publish-docker #20: Commit 0ed1e4d pushed by lvhan028
August 7, 2023 04:48 30d 0h 0m 4s main
August 7, 2023 04:48 30d 0h 0m 4s
Support serving with gradio without communicating to TIS (#162)
publish-docker #19: Commit 18c386d pushed by lvhan028
August 4, 2023 11:38 30d 0h 0m 3s main
August 4, 2023 11:38 30d 0h 0m 3s
Move lmdeploy/turbomind/utils.py to lmdeploy/utils.py (#191)
publish-docker #18: Commit 7a2128b pushed by lvhan028
August 3, 2023 06:07 30d 0h 0m 3s main
August 3, 2023 06:07 30d 0h 0m 3s
Fix build test error and move turbmind csrc test cases to `tests/csrc…
publish-docker #17: Commit 44a8554 pushed by lvhan028
August 3, 2023 06:06 30d 0h 0m 2s main
August 3, 2023 06:06 30d 0h 0m 2s
Support Runtime tensor parallelism (#158)
publish-docker #16: Commit 4767b04 pushed by lvhan028
July 31, 2023 12:48 19h 37m 3s main
July 31, 2023 12:48 19h 37m 3s
[Fix] Remove unused code to reduce binary size (#181)
publish-docker #15: Commit 981a461 pushed by lvhan028
July 31, 2023 08:36 30d 0h 0m 3s main
July 31, 2023 08:36 30d 0h 0m 3s
bump version to v0.0.2 (#177)
publish-docker #14: Commit 7e0b75b pushed by lvhan028
July 28, 2023 07:11 54m 7s v0.0.2
July 28, 2023 07:11 54m 7s
bump version to v0.0.2 (#177)
publish-docker #13: Commit 7e0b75b pushed by lvhan028
July 28, 2023 07:10 30d 0h 0m 3s main
July 28, 2023 07:10 30d 0h 0m 3s
add model_name param for chatbot (#174)
publish-docker #12: Commit 7bc8d17 pushed by lvhan028
July 27, 2023 03:40 30d 0h 0m 3s main
July 27, 2023 03:40 30d 0h 0m 3s
Add manylinux builder (#164)
publish-docker #11: Commit b900471 pushed by lvhan028
July 27, 2023 03:10 30d 0h 0m 2s main
July 27, 2023 03:10 30d 0h 0m 2s
Add triton_models to whl package (#163)
publish-docker #10: Commit e7bc11b pushed by lvhan028
July 26, 2023 06:06 30d 0h 0m 3s main
July 26, 2023 06:06 30d 0h 0m 3s
support fmha gqa (#160)
publish-docker #9: Commit 5ed6bb5 pushed by lzhangzz
July 25, 2023 11:59 1h 44m 19s main
July 25, 2023 11:59 1h 44m 19s
fix getting package root path error in python3.9 (#157)
publish-docker #8: Commit 5203c85 pushed by grimoire
July 25, 2023 03:25 30d 0h 0m 3s main
July 25, 2023 03:25 30d 0h 0m 3s
[Feature] decode-only forward pass (#153)
publish-docker #7: Commit 0cc9d09 pushed by lvhan028
July 24, 2023 06:56 1h 14m 14s main
July 24, 2023 06:56 1h 14m 14s
Refactor the chat template of supported models using factory pattern …
publish-docker #6: Commit 7b470f0 pushed by lvhan028
July 23, 2023 11:35 49m 40s main
July 23, 2023 11:35 49m 40s
add profile throughput benchmark (#146)
publish-docker #5: Commit 2067862 pushed by lvhan028
July 22, 2023 06:20 6h 41m 53s main
July 22, 2023 06:20 6h 41m 53s
remove slicing reponse and add resume api (#154)
publish-docker #4: Commit b728064 pushed by lvhan028
July 21, 2023 13:22 30d 0h 0m 4s main
July 21, 2023 13:22 30d 0h 0m 4s
[Feature] Support Llama-2 with GQA (#147)
publish-docker #3: Commit f07b697 pushed by lvhan028
July 21, 2023 02:46 6h 37m 52s main
July 21, 2023 02:46 6h 37m 52s
[Fix] Support DeepSpeed on autoTP and kernel injection (#138)
publish-docker #2: Commit 2a47547 pushed by lvhan028
July 21, 2023 02:42 30d 0h 0m 3s main
July 21, 2023 02:42 30d 0h 0m 3s
Add github action for publishing docker image (#148)
publish-docker #1: Commit 1a665a6 pushed by RunningLeon
July 21, 2023 01:32 51m 15s main
July 21, 2023 01:32 51m 15s
ProTip! You can narrow down the results and go further in time using created:<2023-07-21 or the other filters available.