Skip to content

Pull requests: InternLM/lmdeploy

New pull request New
70 Open 2,190 Closed
70 Open 2,190 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

[WIP]: Support mtp + dp
#4611 opened May 21, 2026 by RunningLeon Collaborator Loading…
3
fix memleak when input contain large image data
#4610 opened May 21, 2026 by grimoire Collaborator Loading…
3
cancel in-progress runs when PR is updated or merged
#4609 opened May 21, 2026 by lvhan028 Collaborator Loading…
4
TEST: update qwen3.5 397b test
#4607 opened May 21, 2026 by littlegy Contributor Loading…
TEST: update video test
#4606 opened May 21, 2026 by littlegy Contributor Loading…
perf: optimize guided decoding with xgrammar upgrade, batched API, and async D2H overlap
#4605 opened May 21, 2026 by windreamer Collaborator Loading…
1 of 4 tasks
21
Remove state init improvement
#4604 opened May 20, 2026 by grimoire Collaborator Loading…
3
fix(vl): reduce multimodal feature memory use
#4603 opened May 20, 2026 by CUHKSZzxy Collaborator Loading…
3
support qwen3.5(vit) inference in turbomind backend enhancement New feature or request
#4602 opened May 20, 2026 by irexyc Collaborator Loading…
4
[ci] add k4v2 testcase and fix some fail cases
#4601 opened May 20, 2026 by zhulinJulia24 Collaborator Loading…
5
Intern s2 preview lite awq fix bug
#4600 opened May 19, 2026 by 43758726 Collaborator Loading…
8
[WIP]: Support reuse routed experts on eviction
#4599 opened May 19, 2026 by RunningLeon Collaborator Loading…
2
Extend v1/messages by introducing token-in/out and returning routed experts improvement
#4597 opened May 19, 2026 by lvhan028 Collaborator Loading…
5
Refactor proxy server improvement
#4596 opened May 18, 2026 by lvhan028 Collaborator • Draft
8
update anthropic endpoint test
#4594 opened May 18, 2026 by littlegy Contributor Loading…
1
fix(pytorch): offload guided decoding CPU ops to thread pool to prevent event loop blocking improvement
#4590 opened May 18, 2026 by windreamer Collaborator Loading…
3 of 4 tasks
23
docs(advance): add Add a New Speculative Decoding Method guide documentation Improvements or additions to documentation
#4589 opened May 17, 2026 by SuperMarioYL Loading…
4 tasks done
3
refactor ascend multinode
#4588 opened May 15, 2026 by yao-fengchen Collaborator • Draft
Add OpenAI Responses-compatible endpoint enhancement New feature or request
#4582 opened May 13, 2026 by CUHKSZzxy Collaborator Loading…
4
[security] fix(proxy): require auth for node management
#4579 opened May 11, 2026 by Hinotoi-agent Loading…
5 of 9 tasks
2
feat: configure cudagraph capture batch sizes
#4573 opened May 8, 2026 by CUHKSZzxy Collaborator • Draft
Fix health latency under concurrent VL request preparation Bug:P0
#4570 opened May 7, 2026 by CUHKSZzxy Collaborator Loading…
11
LLM evaluation skill on text datasets
#4566 opened Apr 30, 2026 by lvhan028 Collaborator Loading…
9
FP8 kv cache quantization enhancement New feature or request
#4563 opened Apr 29, 2026 by CUHKSZzxy Collaborator Loading…
9
[Feature] Add guided decoding support for speculative decoding enhancement New feature or request
#4559 opened Apr 28, 2026 by windreamer Collaborator Loading…
4 tasks done
1
77
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.