Skip to content

Pull requests: InternLM/lmdeploy

New pull request New
71 Open 2,354 Closed
71 Open 2,354 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

refactor: split api server endpoints improvement
#4797 opened Jul 28, 2026 by lvhan028 Collaborator Loading…
6
SM90 native BF16/FP8 GEMM kernels, fused-SiLU quantization, and linear test harness improvement
#4795 opened Jul 28, 2026 by lzhangzz Collaborator Loading…
5
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
[Bugfix] Fix PyTorch H2D input lifetime across CUDA streams Bug:P1
#4792 opened Jul 28, 2026 by grimoire Collaborator Loading…
2
bump version to v0.15.0
#4791 opened Jul 28, 2026 by lvhan028 Collaborator Loading…
1
[WIP]: Support dflash for qwen3.5
#4789 opened Jul 27, 2026 by RunningLeon Collaborator • Draft
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
2
feat: support Intern-S2-Preview TS forecaster enhancement New feature or request
#4780 opened Jul 24, 2026 by CUHKSZzxy Collaborator Loading…
6
TEST: update turbomind qwen3.5 config
#4778 opened Jul 24, 2026 by littlegy Contributor Loading…
2
[Fix] completions_v1: abort session and return 400 on client disconnect
#4777 opened Jul 23, 2026 by AmirF194 Loading…
1
1
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…
6
feat: support GLM-5.2
#4737 opened Jul 7, 2026 by CUHKSZzxy Collaborator Loading…
6
refactor: isolate XML tool parser state
#4736 opened Jul 6, 2026 by lvhan028 Collaborator Loading…
Add TurboMind ViT support for InternVL and Qwen VL models
#4719 opened Jun 29, 2026 by irexyc Collaborator Loading…
5
refactor: rename quant policy to kv cache dtype
#4718 opened Jun 29, 2026 by CUHKSZzxy Collaborator • Draft
refactor: rename vl package to multimodal BC-breaking
#4710 opened Jun 26, 2026 by CUHKSZzxy Collaborator • Draft
feat: share multimodal hash helpers enhancement New feature or request
#4704 opened Jun 24, 2026 by CUHKSZzxy Collaborator Loading…
8
Fix stale prefix cache hit rate metric
#4699 opened Jun 22, 2026 by DavinciEvans Loading…
2
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
ProTip! Follow long discussions with comments:>50.