Skip to content

Pull requests: InternLM/lmdeploy

New pull request New
24 Open 1,130 Closed
24 Open 1,130 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Flatten cache and add flashattention
#2676 opened Oct 29, 2024 by grimoire Loading…
Call cuda empty_cache to prevent OOM when quantizing model
#2671 opened Oct 28, 2024 by AllentDan Loading…
feat: support dynamic ntk scaling rotary embedding in ascend graph mode
#2670 opened Oct 28, 2024 by tangzhiyi11 • Draft
[ci] support v100 dailytest
#2665 opened Oct 25, 2024 by zhulinJulia24 Loading…
Bump version to v0.6.2
#2659 opened Oct 25, 2024 by lvhan028 Loading…
1
add linear op on dlinfer platform
#2627 opened Oct 21, 2024 by yao-fengchen • Draft
support release pipeline improvement
#2581 opened Oct 11, 2024 by irexyc Loading…
3
support yarn in turbomind backend enhancement New feature or request
#2519 opened Sep 26, 2024 by irexyc Loading…
8
Torchrun launching multiple api_server
#2402 opened Aug 30, 2024 by AllentDan Loading…
2
More w8a8 models
#2373 opened Aug 26, 2024 by AllentDan • Draft
[Feature] Support vision module w8a8 inference improvement
#2308 opened Aug 14, 2024 by AllentDan Loading…
5
better formatted table of 'lmdeploy list' improvement WIP
#2289 opened Aug 12, 2024 by lvhan028 Loading…
2
[Feature] support qqq(w4a8) for lmdeploy
#2274 opened Aug 9, 2024 by HandH1998 Loading…
6 tasks done
@lzhangzz @zhyncs
16
[Feature] Support XTuner Lite Llava enhancement New feature or request
#2191 opened Jul 31, 2024 by pppppM Loading…
1
Add prefix cache stats to usage
#2018 opened Jul 13, 2024 by ispobock Loading…
22
feat: decouple input_ids and output_ids
#1855 opened Jun 25, 2024 by zhyncs Loading…
1
Add Jetson platform support (by docker)
#1820 opened Jun 21, 2024 by BestAnHongjun Loading…
support vl benchmark
#1662 opened May 27, 2024 by AllentDan Loading…
12
[benchmark] optimize benchmark: counting tokenlizer tokens and error requests
#1607 opened May 17, 2024 by NiuBlibing Loading…
5
support AI4Chem/ChemLLM-7B-Chat-1_5-SFT WIP
#1552 opened May 7, 2024 by lvhan028 Loading…
fix: update api_server_backend.py to adapt latest gradio improvement
#1541 opened May 3, 2024 by kv-chiu Loading…
6
Log stats enhancement New feature or request
#1423 opened Apr 11, 2024 by AllentDan Loading…
4
support frequency penalty
#713 opened Nov 20, 2023 by RytonLi Loading…
Visualize layer activations and weights to simplify the quantization process.
#607 opened Oct 24, 2023 by HIT-cwh Loading…
6
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.