Skip to content

Pull requests: InternLM/lmdeploy

New pull request New
78 Open 2,365 Closed
78 Open 2,365 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

Support Interns2 mobius
#4816 opened Aug 3, 2026 by RunningLeon Collaborator Loading…
5
feat: add Hy3 support, MTP, and FP8 optimizations
#4815 opened Aug 3, 2026 by yidingcheng0206 Collaborator • Draft
docs: note OpenAI client base_url for multi-model gateways
#4814 opened Aug 3, 2026 by seven7763 Loading…
3 tasks
fix(disagg): use JSON instead of pickle for P2P ZMQ requests (#4804)
#4812 opened Aug 2, 2026 by Anai-Guo Contributor Loading…
3 tasks done
1
[Bugfix] Return the client-disconnect error instead of discarding it in completions_v1
#4811 opened Jul 31, 2026 by ErenAta16 Loading…
3 tasks done
1
2
feat: support interns2 preview time-series encoder
#4810 opened Jul 31, 2026 by CUHKSZzxy Collaborator • Draft
perf(pytorch): add opt-in torch.compile for decode CUDA graphs improvement
#4808 opened Jul 31, 2026 by grimoire Collaborator Loading…
3
[ci] remove old models and refactor interface testcase
#4806 opened Jul 30, 2026 by zhulinJulia24 Collaborator • Draft
refactor(pytorch): derive CUDA step metadata from selected operators
#4805 opened Jul 30, 2026 by grimoire Collaborator Loading…
1
fix(serve): reject empty/falsy prompt input in format_prompts and AsyncEngine.generate
#4803 opened Jul 29, 2026 by SuperMarioYL Loading…
3
refactor: stream tool parameters incrementally improvement
#4802 opened Jul 29, 2026 by lvhan028 Collaborator Loading…
3
Ssm prefix cache non aligned
#4799 opened Jul 29, 2026 by grimoire Collaborator • Draft
1 of 2 tasks
refactor: split api server endpoints improvement
#4797 opened Jul 28, 2026 by lvhan028 Collaborator Loading…
6
feat: add Rust TurboMind API server
#4794 opened Jul 28, 2026 by lvhan028 Collaborator • Draft
3
[Feat]: Support output input logprobs enhancement New feature or request
#4793 opened Jul 28, 2026 by RunningLeon Collaborator Loading…
5
Support dflash for qwen3.5 enhancement New feature or request
#4789 opened Jul 27, 2026 by RunningLeon Collaborator Loading…
2
optimize and modularize SSM prefix caching improvement
#4788 opened Jul 27, 2026 by grimoire Collaborator Loading…
2
Integrate DeepEPv2 enhancement New feature or request
#4783 opened Jul 25, 2026 by irexyc Collaborator Loading…
7
[Fix] generate: propagate the disconnect 400 instead of returning null
#4782 opened Jul 24, 2026 by AmirF194 Loading…
1
4
feat: support Intern-S2-Preview TS forecaster enhancement New feature or request
#4780 opened Jul 24, 2026 by CUHKSZzxy Collaborator Loading…
10
TEST: update turbomind qwen3.5 config
#4778 opened Jul 24, 2026 by littlegy Contributor Loading…
2
fix(security): reject pickled update_weights payloads by default
#4765 opened Jul 21, 2026 by Solaris-star Loading…
1
[Draft] Add PyTorch engine support for Hy3 BF16 and static FP8 (NO MTP)
#4763 opened Jul 20, 2026 by yidingcheng0206 Collaborator • Draft
5 of 7 tasks
3
Upgrade to cu130
#4753 opened Jul 15, 2026 by RunningLeon Collaborator Loading…
10
feat: support GLM-5.2 enhancement New feature or request
#4737 opened Jul 7, 2026 by CUHKSZzxy Collaborator Loading…
11
ProTip! Exclude everything labeled bug with -label:bug.