Skip to content

Pull requests: InternLM/lmdeploy

New pull request New
55 Open 2,021 Closed
55 Open 2,021 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: change debug log from ERROR to DEBUG in RepetitionPenaltyKernel
#4363 opened Feb 15, 2026 by murray-macdonald Loading…
GLM-4.7-Flash Turbomind support
#4362 opened Feb 13, 2026 by lapy Loading…
2 of 4 tasks
2
fix fa3 install
#4361 opened Feb 13, 2026 by irexyc Loading…
2
[WIP] Support video inputs
#4360 opened Feb 13, 2026 by CUHKSZzxy • Draft
fix ssm inputs merge
#4359 opened Feb 13, 2026 by grimoire Loading…
2
ci(lint): skip flaky deadlink test for python wiki page
#4357 opened Feb 13, 2026 by windreamer Loading…
2
support glm5
#4355 opened Feb 12, 2026 by grimoire Loading…
2
Improve proxy server improvement
#4354 opened Feb 12, 2026 by lvhan028 Loading…
2
Qwen3.5
#4351 opened Feb 11, 2026 by grimoire Loading…
2
Fix XGrammar bitmask initialization and add null check for gen_config in generate method
#4349 opened Feb 11, 2026 by windreamer Loading…
13
[WIP]: support glm4.7 with mtp WIP
#4346 opened Feb 10, 2026 by RunningLeon • Draft
Support MiniMax-M2 in TurboMind engine
#4343 opened Feb 10, 2026 by zh-nj Loading…
9
Fix authorization Bug:P1
#4338 opened Feb 9, 2026 by lvhan028 Loading…
30
[WIP]Support torch compile
#4336 opened Feb 8, 2026 by grimoire • Draft
add preliminary support for EP(single-node) of turbomind backend
#4332 opened Feb 6, 2026 by irexyc Loading…
2
Qwen/Internlm/Llama Dense/Moe model fp8 quant online enhancement New feature or request
#4324 opened Feb 5, 2026 by 43758726 Loading…
6
Compatible with transformers 5.0 at TurboMind side improvement
#4304 opened Jan 28, 2026 by lvhan028 Loading…
3
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
support repetition ngram logits processor enhancement New feature or request
#4288 opened Jan 23, 2026 by grimoire Loading…
8
fix dllm mask on set_step
#4278 opened Jan 18, 2026 by grimoire Loading…
3
[ascend] fix awq and smoothq
#4277 opened Jan 16, 2026 by wanfengcxz • Draft
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
Support fp32 head for qwen and internlm models improvement
#4160 opened Nov 27, 2025 by RunningLeon Loading…
15
ProTip! no:milestone will show everything without a milestone.