Skip to content

Pull requests: InternLM/lmdeploy

New pull request New
47 Open 1,586 Closed
47 Open 1,586 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

upgrade torch and triton
#3677 opened Jun 26, 2025 by grimoire Loading…
ray close wait for forward finish
#3676 opened Jun 26, 2025 by grimoire • Draft
Support load fused moe weights enhancement New feature or request
#3672 opened Jun 26, 2025 by RunningLeon Loading…
fix free cache in MPEngine branch
#3670 opened Jun 25, 2025 by JimyMa Loading…
Reduce sampling memory usage improvement
#3666 opened Jun 24, 2025 by lzhangzz Loading…
add reward model api enhancement New feature or request
#3665 opened Jun 24, 2025 by CUHKSZzxy Loading…
1
custom triton cache manager
#3659 opened Jun 20, 2025 by grimoire Loading…
Refactor linear improvement
#3653 opened Jun 19, 2025 by grimoire Loading…
1
update twomicrobatch
#3651 opened Jun 18, 2025 by SHshenhao Loading…
3
support do_preprocess=False for chat.completions
#3645 opened Jun 16, 2025 by irexyc Loading…
remove python3.8 support and add python3.13 support improvement
#3638 opened Jun 12, 2025 by lvhan028 Loading…
raise ImportError when enable ep and not install dlblas improvement
#3636 opened Jun 11, 2025 by zhaochaoxing Loading…
5
Seperate api_server and pytorch engine into different processors enhancement New feature or request
#3627 opened Jun 9, 2025 by grimoire Loading…
10
FA3 enhancement New feature or request
#3623 opened Jun 9, 2025 by zhaochaoxing Loading…
9
[Feature] metrics support enhancement New feature or request WIP
#3534 opened May 9, 2025 by CUHKSZzxy Loading…
8 of 9 tasks
14
Update batched dynamic ntk
#3468 opened Apr 22, 2025 by grimoire Loading…
Opt moe block by dlblas, when ep > 1
#3461 opened Apr 21, 2025 by hellozmz • Draft
Zmz/prefill without permute by dlblas
#3430 opened Apr 14, 2025 by hellozmz • Draft
1
[WIP]: vl prefix caching
#3389 opened Apr 3, 2025 by RunningLeon Loading…
1
Add Gloo communication to turobmind enhancement New feature or request
#3362 opened Mar 28, 2025 by irexyc Loading…
4
[maca] support multinode for maca.
#3340 opened Mar 26, 2025 by Reinerzhou • Draft
1
Create SECURITY.md
#3333 opened Mar 25, 2025 by ybdesire Loading…
1
Improve turbomind's prefix cache BC-breaking improvement
#3332 opened Mar 25, 2025 by lvhan028 Loading…
6 of 8 tasks
1
add deepseekv3 doc documentation Improvements or additions to documentation WIP
#3265 opened Mar 17, 2025 by CUHKSZzxy Loading…
1
support loading model with user input params (turbomind) enhancement New feature or request
#3204 opened Mar 3, 2025 by irexyc Loading…
1
ProTip! What’s not been updated in a month: updated:<2025-05-26.