Skip to content

Issues: sgl-project/sglang

Development Roadmap (2024 Q4)
#1487 opened Sep 21, 2024 by Ying1123
Open 1
Development Roadmap (2024 Q3)
#634 opened Jul 17, 2024 by Ying1123
Open 18
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

59 Open 485 Closed
59 Open 485 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[doc] Chinese Documentation Translation Available for sglang
#1565 opened Oct 4, 2024 by khum08
2 tasks done
[Feature] Add choices in /generate endpoint and add min_new_tokens in sgl.gen()
#1564 opened Oct 4, 2024 by TING2938
2 tasks done
Print out what the model saw?
#1560 opened Oct 3, 2024 by cinjon
[Bug] Exception: Capture cuda graph failed: Triton Error [CUDA]: device kernel image is invalid
#1558 opened Oct 3, 2024 by a136214808
1 of 5 tasks
[Bug] ValueError: The memory capacity is unbalanced
#1533 opened Sep 29, 2024 by chuangzhidan
4 of 5 tasks
[Bug] add support for llama 3.2
#1523 opened Sep 26, 2024 by Stealthwriter
5 tasks done
3
[Bug] unable to use all three combined: data-parallelism(dp), enable-torch-compile, cuda-graph (8*A40)
#1522 opened Sep 26, 2024 by smallstepman
5 tasks done
6
Accuracy reduction of Lora
#1519 opened Sep 26, 2024 by yileld
@Ying1123
1
[Bug] no module modelscope using docker compose to start sglang
#1517 opened Sep 26, 2024 by KylinMountain
2 of 5 tasks
2
[Feature] _get_pixel_values needs to return tgt_sizes
#1514 opened Sep 26, 2024 by huangzl18883
2 tasks done
[Bug] LLaVa-next does not work for single image processing
#1506 opened Sep 24, 2024 by ThomasBenzshawel
5 tasks done
AWQ performance tracking performance
#1505 opened Sep 24, 2024 by zhyncs
2 tasks
@ispobock @zhyncs
1
Possible timing side-channels caused by shared prefix
#1504 opened Sep 24, 2024 by Unik-lif
Development Roadmap (2024 Q4)
#1487 opened Sep 21, 2024 by Ying1123
1 of 31 tasks
1
[Bug] Llama 405B FP8 causes OOM on 16xA40
#1439 opened Sep 16, 2024 by sumukshashidhar
5 tasks done
1
[Feature] Expert parallelism support enhancement New feature or request
#1435 opened Sep 16, 2024 by chongli-uw
2 tasks done
@merrymercy @ispobock @zhyncs
1
[Bug] OpenAI batch API gets stuck
#1415 opened Sep 13, 2024 by dmakhervaks
5 tasks
6
[Bug] RuntimeError: Failed to allocate memory for batch_prefill_tmp_v with size 458752000 and alignment 16 in AlignedAllocator
#1405 opened Sep 12, 2024 by josephydu
5 tasks done
@zhyncs
9
[Feature] support awq of deepseek-v2 or deepseek-v2.5
#1396 opened Sep 12, 2024 by tutu329
2 tasks done
@ispobock @zhyncs
[Feature] Support torch profiler good first issue Good for newcomers
#1388 opened Sep 11, 2024 by danielhua23
2 tasks done
2
[Feature] Support RM API high priority
#1384 opened Sep 11, 2024 by UbeCc
2 tasks done
@Ying1123
3
[Bug] too many processes
#1382 opened Sep 11, 2024 by wellhowtosay
5 tasks
1
[Feature] 4-bit quantized prefix cache enhancement New feature or request
#1374 opened Sep 10, 2024 by josephrocca
3
[Feature] support LLaVA-NeXT-Video-32B-Qwen
#1356 opened Sep 9, 2024 by HarperGG
2 tasks done
2
[Feature] support qwen2 vl
#1352 opened Sep 8, 2024 by zhyncs
2 tasks done
@ispobock @zhyncs
4
ProTip! Add no:assignee to see everything that’s not assigned.