Skip to content

Pull requests: InternLM/lmdeploy

New pull request New
71 Open 2,310 Closed
71 Open 2,310 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

Update multimodal toolcall tests
#4742 opened Jul 8, 2026 by littlegy Contributor • Draft
[WIP]: fix deepep mtp
#4741 opened Jul 7, 2026 by RunningLeon Collaborator Loading…
5
feat: add AgRs all2all backend
#4739 opened Jul 7, 2026 by irexyc Collaborator • Draft
Guard DP dummy inputs around pending work improvement
#4738 opened Jul 7, 2026 by grimoire Collaborator Loading…
1
feat: support GLM-5.2
#4737 opened Jul 7, 2026 by CUHKSZzxy Collaborator • Draft
refactor: isolate XML tool parser state
#4736 opened Jul 6, 2026 by lvhan028 Collaborator Loading…
fix: restrict remote media domains
#4734 opened Jul 6, 2026 by CUHKSZzxy Collaborator Loading…
5
Remove interactive v2
#4730 opened Jul 3, 2026 by lvhan028 Collaborator • Draft
3
clear runtime state in sleep improvement
#4729 opened Jul 3, 2026 by grimoire Collaborator Loading…
2
refactor(pytorch): clarify scheduler and input-maker control flow
#4727 opened Jul 2, 2026 by grimoire Collaborator Loading…
2
feat: add deepseek v3.2 and v4 chat templates
#4724 opened Jun 30, 2026 by CUHKSZzxy Collaborator • Draft
Add TurboMind ViT support for InternVL and Qwen VL models
#4719 opened Jun 29, 2026 by irexyc Collaborator • Draft
refactor: rename quant policy to kv cache dtype
#4718 opened Jun 29, 2026 by CUHKSZzxy Collaborator • Draft
feat(turbomind): memory allocator, object cache, and scheduler integration enhancement New feature or request
#4717 opened Jun 29, 2026 by lzhangzz Collaborator Loading…
3
refactor: rename vl package to multimodal BC-breaking
#4710 opened Jun 26, 2026 by CUHKSZzxy Collaborator • Draft
feat(serve): add --generation-config CLI for server sampling defaults improvement
#4708 opened Jun 25, 2026 by lvhan028 Collaborator Loading…
8
feat: share multimodal hash helpers enhancement New feature or request
#4704 opened Jun 24, 2026 by CUHKSZzxy Collaborator Loading…
6
Fix stale prefix cache hit rate metric
#4699 opened Jun 22, 2026 by DavinciEvans Loading…
2
Remove interactive chat and make inference stateless
#4694 opened Jun 22, 2026 by lvhan028 Collaborator • Draft
5
fix: gate multimodal preprocessing concurrency
#4687 opened Jun 17, 2026 by CUHKSZzxy Collaborator Loading…
5
Batch invariant support PART1
#4666 opened Jun 10, 2026 by grimoire Collaborator • Draft
4
refactor(proxy): split monolithic proxy into modular serve/proxy package improvement
#4647 opened Jun 4, 2026 by lvhan028 Collaborator Loading…
8
feat: add multimodal and preemption metrics
#4640 opened Jun 1, 2026 by CUHKSZzxy Collaborator Loading…
9
modify save model in lite module improvement
#4624 opened May 26, 2026 by 43758726 Contributor Loading…
2
feat(turbomind): support priority schedule policy
#4614 opened May 22, 2026 by 4mengy Loading…
3 of 4 tasks
18
ProTip! Adding no:label will show everything without a label.