Skip to content

Pull requests: InternLM/lmdeploy

New pull request New
32 Open 1,247 Closed
32 Open 1,247 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix torch_dtype in lite
#2956 opened Dec 25, 2024 by AllentDan Loading…
1
Bump version to v0.6.5
#2955 opened Dec 25, 2024 by lvhan028 Loading…
[side-effect] bring back quantization of qwen2-vl, glm4v and etc. Bug:P1
#2954 opened Dec 25, 2024 by lvhan028 Loading…
3
Fallback to pytorch engine when the model is quantized by smooth quant improvement
#2953 opened Dec 25, 2024 by lvhan028 Loading…
9
[dlinfer] feat: add DlinferFlashAttention to support qwen vl.
#2952 opened Dec 25, 2024 by Reinerzhou Loading…
[ci] add w8a8 and internvl2.5 models into testcase
#2949 opened Dec 24, 2024 by zhulinJulia24 Loading…
1
[maca] support deepseekv2 for maca backend. enhancement New feature or request
#2918 opened Dec 18, 2024 by Reinerzhou • Draft
Remove threadsafe improvement
#2907 opened Dec 17, 2024 by grimoire Loading…
9
Support moe w8a8
#2894 opened Dec 13, 2024 by grimoire Loading…
[WIP]: use weights iterator while loading
#2886 opened Dec 12, 2024 by RunningLeon Loading…
support Turbomind ep enhancement New feature or request
#2883 opened Dec 12, 2024 by irexyc Loading…
Support Medusa speculative decoding enhancement New feature or request
#2859 opened Dec 5, 2024 by AllentDan Loading…
2
[maca] add cudagraph support on maca backend.
#2834 opened Nov 29, 2024 by Reinerzhou • Draft
Refactor turbomind attention by precomputing rotary embed improvement
#2801 opened Nov 25, 2024 by irexyc Loading…
11
[Feature] Support llava onevision enhancement New feature or request
#2783 opened Nov 21, 2024 by deepindeed2022 Loading…
13
support qwen2-vl with turbomind backend enhancement New feature or request
#2720 opened Nov 6, 2024 by irexyc Loading…
1
Run loop.run_until_complete in another thread improvement
#2701 opened Nov 4, 2024 by AllentDan Loading…
1
update pre-commit config
#2683 opened Oct 30, 2024 by lvhan028 Loading…
3
support release pipeline improvement
#2581 opened Oct 11, 2024 by irexyc Loading…
3
Torchrun launching multiple api_server improvement
#2402 opened Aug 30, 2024 by AllentDan Loading…
7
[Feature] Support vision module w8a8 inference improvement
#2308 opened Aug 14, 2024 by AllentDan Loading…
5
better formatted table of 'lmdeploy list' improvement WIP
#2289 opened Aug 12, 2024 by lvhan028 Loading…
2
[Feature] support qqq(w4a8) for lmdeploy
#2274 opened Aug 9, 2024 by HandH1998 Loading…
6 tasks done
@lzhangzz @zhyncs
16
[Feature] Support XTuner Lite Llava enhancement New feature or request
#2191 opened Jul 31, 2024 by pppppM Loading…
1
Add prefix cache stats to usage
#2018 opened Jul 13, 2024 by ispobock Loading…
23
ProTip! Follow long discussions with comments:>50.