Skip to content

Actions: InternLM/lmdeploy

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
21 workflow run results
21 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

rename readthedocs config file (#429)
publish-docker #77: Commit 19ff47d pushed by lvhan028
September 19, 2023 02:47 30d 0h 0m 4s main
September 19, 2023 02:47 30d 0h 0m 4s
[Fix] Support actual seqlen in flash-attention2 (#418)
publish-docker #76: Commit abe9f7b pushed by lvhan028
September 18, 2023 12:38 30d 0h 0m 3s main
September 18, 2023 12:38 30d 0h 0m 3s
Fix token count bug (#416)
publish-docker #75: Commit 3a7880a pushed by lvhan028
September 18, 2023 12:04 30d 0h 0m 3s main
September 18, 2023 12:04 30d 0h 0m 3s
Reduce gil switching (#407)
publish-docker #74: Commit d44a8bf pushed by lvhan028
September 18, 2023 12:03 30d 0h 0m 4s main
September 18, 2023 12:03 30d 0h 0m 4s
Fix memory leak (#415)
publish-docker #73: Commit 2dec28a pushed by lvhan028
September 14, 2023 12:56 30d 0h 0m 4s main
September 14, 2023 12:56 30d 0h 0m 4s
fix output[-1] when output is empty (#405)
publish-docker #72: Commit 64c39dd pushed by lvhan028
September 13, 2023 06:33 30d 0h 0m 3s main
September 13, 2023 06:33 30d 0h 0m 3s
more general pypi ci (#412)
publish-docker #71: Commit 2537c5e pushed by lvhan028
September 13, 2023 03:18 30d 0h 0m 4s main
September 13, 2023 03:18 30d 0h 0m 4s
[Fix] Update puyu model (#399)
publish-docker #68: Commit cfec5be pushed by lvhan028
September 11, 2023 08:18 30d 0h 0m 4s main
September 11, 2023 08:18 30d 0h 0m 4s
Support codellama (#359)
publish-docker #67: Commit 65c662f pushed by lvhan028
September 11, 2023 05:09 30d 0h 0m 4s main
September 11, 2023 05:09 30d 0h 0m 4s
Support baichuan2-chat chat template (#378)
publish-docker #66: Commit 55764e0 pushed by lvhan028
September 8, 2023 09:03 30d 0h 0m 3s main
September 8, 2023 09:03 30d 0h 0m 3s
fix exceed session len core dump for chat and generate (#366)
publish-docker #65: Commit ce21a31 pushed by lvhan028
September 7, 2023 10:38 30d 0h 0m 3s main
September 7, 2023 10:38 30d 0h 0m 3s
[Fix] Set max dynamic smem size for decoder MHA to support context le…
publish-docker #64: Commit 71ade77 pushed by lvhan028
September 7, 2023 10:38 30d 0h 0m 4s main
September 7, 2023 10:38 30d 0h 0m 4s
bug-fix: always use stream mode to enable persistent batching (#346)
publish-docker #63: Commit 57cf99b pushed by lvhan028
September 7, 2023 09:42 30d 0h 0m 3s main
September 7, 2023 09:42 30d 0h 0m 3s
bump version to v0.0.7 (#358)
publish-docker #61: Commit d065f3e pushed by lvhan028
September 4, 2023 06:38 30d 0h 0m 4s main
September 4, 2023 06:38 30d 0h 0m 4s
Fix profile_serving hung issue (#344)
publish-docker #60: Commit edb7c6e pushed by lvhan028
September 4, 2023 03:07 30d 0h 0m 3s main
September 4, 2023 03:07 30d 0h 0m 3s
Decode generated token_ids incrementally (#309)
publish-docker #59: Commit 9bfe03c pushed by lvhan028
September 1, 2023 08:39 30d 0h 0m 3s main
September 1, 2023 08:39 30d 0h 0m 3s
Package 'bin/llama_gemm' to wheel (#320)
publish-docker #58: Commit 22e8b2c pushed by lvhan028
September 1, 2023 04:16 30d 0h 0m 2s main
September 1, 2023 04:16 30d 0h 0m 2s
Add flashattention2 (#196)
publish-docker #57: Commit 452822a pushed by lvhan028
August 29, 2023 12:53 30d 0h 0m 2s main
August 29, 2023 12:53 30d 0h 0m 2s
Fix turbomind import error on windows (#316)
publish-docker #56: Commit d4d609b pushed by lvhan028
August 29, 2023 08:14 30d 0h 0m 3s main
August 29, 2023 08:14 30d 0h 0m 3s
fix(kvint8): update doc (#315)
publish-docker #55: Commit a48e2d2 pushed by lvhan028
August 29, 2023 05:50 30d 0h 0m 3s main
August 29, 2023 05:50 30d 0h 0m 3s
Fix readthedocs building (#321)
publish-docker #54: Commit 08b2812 pushed by lvhan028
August 29, 2023 02:28 30d 0h 0m 3s main
August 29, 2023 02:28 30d 0h 0m 3s