Skip to content

Pull requests: InternLM/lmdeploy

New pull request New
58 Open 2,069 Closed
58 Open 2,069 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

Optimize Qwen3.5 improvement
#4434 opened Mar 19, 2026 by lzhangzz Loading…
6
Split/tool call args json for qwen3coder tool calls (Qwen3.5)
#4433 opened Mar 19, 2026 by lapy Loading…
4
feat: fully implement compressed-tensors gs32 support in TurboMind enhancement New feature or request
#4429 opened Mar 19, 2026 by lapy Loading…
6
update h config and add glm4.7 mtp test
#4424 opened Mar 18, 2026 by littlegy Loading…
1
delete ray remote function return value improvement
#4422 opened Mar 18, 2026 by grimoire Loading…
3
lmdeploy support kernel block size
#4421 opened Mar 17, 2026 by Tsundoku958 Loading…
2
[Feature] Support n parameter in /v1/chat/completions and /v1/completions
#4419 opened Mar 17, 2026 by ziyangliu-666 Loading…
1
10
support cache_seqlen on recurrent-gdr and causal-conv1d-update
#4417 opened Mar 17, 2026 by grimoire Loading…
10
Assign sequential api_server ports when proxy_url is unset
#4416 opened Mar 16, 2026 by lvhan028 Loading…
8
[WIP] Support qwen3-omni
#4411 opened Mar 13, 2026 by CUHKSZzxy • Draft
2 of 4 tasks
fix metrics Bug:P1
#4410 opened Mar 13, 2026 by CUHKSZzxy Loading…
3
[ci] add nightly docker build workflow
#4406 opened Mar 12, 2026 by zhulinJulia24 Loading…
8
Add model deployment best practice section in user guide
#4399 opened Mar 9, 2026 by lvhan028 • Draft
4
[Fix][Feat] Fix worker sorting with external pg bundles & Support persistent buffer for update_params
#4397 opened Mar 6, 2026 by CyCle1024 Loading…
10
[Ascend] support qwen3.5 27B
#4395 opened Mar 4, 2026 by wanfengcxz • Draft
Builtin mrope improvement
#4393 opened Mar 4, 2026 by grimoire Loading…
6
Use pyupgrade and ruff to modernize LMDeploy Python Code
#4392 opened Mar 3, 2026 by windreamer Loading…
5
add tool and reasoning test
#4388 opened Mar 2, 2026 by littlegy Loading…
6
Fix Structured Output for GPT-OSS Models
#4386 opened Mar 2, 2026 by windreamer Loading…
1
9
Improve proxy server improvement
#4354 opened Feb 12, 2026 by lvhan028 Loading…
2
Support MiniMax-M2 in TurboMind engine enhancement New feature or request
#4343 opened Feb 10, 2026 by zh-nj Loading…
9
[WIP]Support torch compile
#4336 opened Feb 8, 2026 by grimoire • Draft
add preliminary support for EP(single-node) of turbomind backend enhancement New feature or request
#4332 opened Feb 6, 2026 by irexyc Loading…
2
change ascend paged attention from BSH format to TND format for better performace
#4295 opened Jan 27, 2026 by jinminxi104 • Draft
return BadRequest for all invlid inputs Bug:P2
#4291 opened Jan 26, 2026 by lvhan028 Loading…
2
ProTip! Add no:assignee to see everything that’s not assigned.