Skip to content

Actions: InternLM/lmdeploy

Actions

publish-docker

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
docker.yml
839 workflow runs
839 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Support mixtral moe AWQ quantization. (#2725) publish-docker #817: Commit adf7c36 pushed by lvhan028
November 13, 2024 04:21 30d 0h 0m 4s main
main
November 13, 2024 04:21 30d 0h 0m 4s
Support Qwen2-MoE models (#2723) publish-docker #816: Commit d2d4209 pushed by lvhan028
November 13, 2024 03:27 30d 0h 0m 3s main
main
November 13, 2024 03:27 30d 0h 0m 3s
fix assert pad >= 0 failed when inter_size is not a multiple of group… publish-docker #815: Commit e751708 pushed by lvhan028
November 12, 2024 13:15 30d 0h 0m 3s main
main
November 12, 2024 13:15 30d 0h 0m 3s
Remove one of the duplicate bos tokens (#2708) publish-docker #814: Commit 67a8538 pushed by lvhan028
November 12, 2024 08:40 30d 0h 0m 3s main
main
November 12, 2024 08:40 30d 0h 0m 3s
Support ep, column major moe kernel. (#2690) publish-docker #813: Commit 4a8d745 pushed by lvhan028
November 11, 2024 13:11 30d 0h 0m 4s main
main
November 11, 2024 13:11 30d 0h 0m 4s
Support Mono-InternVL with PyTorch backend (#2727) publish-docker #812: Commit 06aea5d pushed by lvhan028
November 11, 2024 03:09 30d 0h 0m 2s main
main
November 11, 2024 03:09 30d 0h 0m 2s
[Feature]: support LlavaForConditionalGeneration with turbomind infer… publish-docker #811: Commit 78ab485 pushed by lvhan028
November 8, 2024 11:31 30d 0h 0m 4s main
main
November 8, 2024 11:31 30d 0h 0m 4s
Flatten cache and add flashattention (#2676) publish-docker #810: Commit 2bed018 pushed by lvhan028
November 8, 2024 03:51 30d 0h 0m 2s main
main
November 8, 2024 03:51 30d 0h 0m 2s
bump version to 0.6.2.post1 (#2717) publish-docker #809: Commit 4fc9479 pushed by lvhan028
November 7, 2024 07:41 1h 10m 9s v0.6.2.post1
v0.6.2.post1
November 7, 2024 07:41 1h 10m 9s
fix tp exit code for pytorch engine (#2718) publish-docker #808: Commit a4012ef pushed by lvhan028
November 7, 2024 03:21 30d 0h 0m 3s main
main
November 7, 2024 03:21 30d 0h 0m 3s
support turbomind head_dim 64 (#2715) publish-docker #807: Commit e7886b4 pushed by lvhan028
November 6, 2024 07:27 30d 0h 0m 2s main
main
November 6, 2024 07:27 30d 0h 0m 2s
fix decoding kernel for deepseekv2 (#2688) publish-docker #806: Commit 354028b pushed by lvhan028
November 6, 2024 06:53 30d 0h 0m 2s main
main
November 6, 2024 06:53 30d 0h 0m 2s
Add ensure_ascii = False for json.dumps (#2707) publish-docker #805: Commit cc14215 pushed by lvhan028
November 6, 2024 03:07 30d 0h 0m 2s main
main
November 6, 2024 03:07 30d 0h 0m 2s
add linear op on dlinfer platform (#2627) publish-docker #804: Commit 364a142 pushed by lvhan028
November 5, 2024 11:41 30d 0h 0m 3s main
main
November 5, 2024 11:41 30d 0h 0m 3s
feat: support dynamic/llama3 rotary embedding in ascend graph mode (#… publish-docker #803: Commit ed9aa15 pushed by lvhan028
November 5, 2024 11:39 30d 0h 0m 3s main
main
November 5, 2024 11:39 30d 0h 0m 3s
Fix turbomind TP (#2706) publish-docker #802: Commit 71f1d0f pushed by lvhan028
November 5, 2024 06:32 30d 0h 0m 3s main
main
November 5, 2024 06:32 30d 0h 0m 3s
miss to read moe_ffn weights from converted tm model (#2698) publish-docker #801: Commit 5f577c2 pushed by lvhan028
November 4, 2024 08:55 30d 0h 0m 3s main
main
November 4, 2024 08:55 30d 0h 0m 3s
support yarn in turbomind backend (#2519) publish-docker #800: Commit e557f05 pushed by lvhan028
November 4, 2024 08:30 30d 0h 0m 3s main
main
November 4, 2024 08:30 30d 0h 0m 3s
better tp exit log (#2677) publish-docker #799: Commit 20de959 pushed by lvhan028
November 4, 2024 08:29 30d 0h 0m 2s main
main
November 4, 2024 08:29 30d 0h 0m 2s
fix index error when computing ppl on long-text prompt (#2697) publish-docker #798: Commit 993aa14 pushed by lvhan028
November 1, 2024 12:06 30d 0h 0m 3s main
main
November 1, 2024 12:06 30d 0h 0m 3s
Support min_tokens, min_p parameters for api_server (#2681) publish-docker #797: Commit 654c457 pushed by lvhan028
November 1, 2024 12:05 30d 0h 0m 3s main
main
November 1, 2024 12:05 30d 0h 0m 3s
Call cuda empty_cache to prevent OOM when quantizing model (#2671) publish-docker #796: Commit dde5d23 pushed by lvhan028
October 31, 2024 06:39 30d 0h 0m 3s main
main
October 31, 2024 06:39 30d 0h 0m 3s
Bump version to v0.6.2 (#2659) publish-docker #795: Commit 522108c pushed by lvhan028
October 29, 2024 06:42 1h 14m 35s v0.6.2
v0.6.2
October 29, 2024 06:42 1h 14m 35s
Bump version to v0.6.2 (#2659) publish-docker #794: Commit 522108c pushed by lvhan028
October 29, 2024 06:40 30d 0h 0m 3s main
main
October 29, 2024 06:40 30d 0h 0m 3s
remove dlinfer version (#2672) publish-docker #793: Commit a07e65e pushed by lvhan028
October 28, 2024 11:06 30d 0h 0m 2s main
main
October 28, 2024 11:06 30d 0h 0m 2s