Skip to content

Pull requests: InternLM/lmdeploy

New pull request New
44 Open 1,956 Closed
44 Open 1,956 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

[Fix] fix quant calibration dataset improvement
#4256 opened Jan 5, 2026 by 43758726 Loading…
30
[ascend] fix paged prefill
#4254 opened Jan 5, 2026 by tangzhiyi11 Loading…
1
[AsyncEngine Refactor 3/N] Introduce SessionManager and InstManager
#4253 opened Jan 5, 2026 by lvhan028 Loading…
docs: add generated openapi spec documentation
#4251 opened Jan 4, 2026 by windreamer Loading…
@windreamer
12
[WIP]: Support destroy deepep buffer explicitly improvement WIP
#4246 opened Dec 31, 2025 by RunningLeon Loading…
2
Adapt to dlsime v0.0.2 improvement
#4242 opened Dec 30, 2025 by JimyMa Loading…
13
feat: implement online bf16-to-fp8 conversion and inference in TurboMind improvement
#4237 opened Dec 25, 2025 by 43758726 Loading…
19
Refactor turbomind engine improvement
#4223 opened Dec 19, 2025 by lzhangzz Loading…
4
lmdeploy suppport parrllel embedding improvement
#4192 opened Dec 9, 2025 by Tsundoku958 Loading…
1
28
Update benchmark serving script for proxy_server
#4173 opened Dec 1, 2025 by lvhan028 Loading…
[WIP]: Support prefix caching with routed experts
#4171 opened Nov 28, 2025 by RunningLeon • Draft
fix: Fix Guided Decoding Crashes and State Corruption Issues
#4167 opened Nov 28, 2025 by windreamer Loading…
1
@windreamer
22
[WIP]: Support fp32 head for qwen and internlm models
#4160 opened Nov 27, 2025 by RunningLeon • Draft
fix: fix lora weight loading for internvl
#4106 opened Nov 6, 2025 by windreamer • Draft
Update installation.md
#4095 opened Nov 3, 2025 by krescent Loading…
1
Add step_map to track token decoding order in DLLM
#4057 opened Oct 21, 2025 by Auraithm Loading…
4 tasks done
4
[POC] Encoder Disaggregation
#4047 opened Oct 17, 2025 by CUHKSZzxy • Draft
2 of 7 tasks
quant blocked fp8 enhancement New feature or request
#4018 opened Sep 29, 2025 by CUHKSZzxy Loading…
4 of 5 tasks
8
Add reasoning parser for GPT-OSS style channels.
#3998 opened Sep 21, 2025 by GY19A Loading…
1
[PD Disaggregation] remote recomputation preemption
#3854 opened Aug 18, 2025 by JimyMa Loading…
add ppu quick start doc documentation Improvements or additions to documentation
#3841 opened Aug 14, 2025 by guozixu2001 Loading…
9
support pp in turbomind
#3768 opened Jul 24, 2025 by irexyc • Draft
1 task
fix: qwen3 nonstream parse with no or uncompleted think content
#3748 opened Jul 18, 2025 by ywx217 Loading…
10
fix: make project PEP 517 compliant.
#3738 opened Jul 17, 2025 by windreamer Loading…
5 tasks done
1
Add dp rank into proxy node status
#3720 opened Jul 8, 2025 by RunningLeon Loading…
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.