Skip to content

Issues: sgl-project/sglang

Development Roadmap (2024 Q4)
#1487 opened Sep 21, 2024 by Ying1123
Open 21
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

123 Open 652 Closed
123 Open 652 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

[Feature] (Willing to PR) Avoid KV cache occupying GPU memory when not used feature
#2542 opened Dec 22, 2024 by fzyzcjy
2 tasks done
@zhaochenyang20
1
[Bug] Eagle2 has an unstable sampling rate during multi concurrency。
#2537 opened Dec 21, 2024 by coolhok
5 tasks done
[Bug] Transformers doesn't recognize LLaVA variant architectures
#2532 opened Dec 20, 2024 by amosyou
5 tasks done
How to do quantization
#2531 opened Dec 20, 2024 by binhtranmcs
[Bug] SGLang v0.4.0 with AMD MI300X
#2530 opened Dec 20, 2024 by BruceXcluding
5 tasks done
1
sglang for Qwen2.5-14b deploy Error
#2520 opened Dec 19, 2024 by wuxianyess
@ispobock @HandH1998
1
Is video inference supported?
#2519 opened Dec 19, 2024 by wuxianyess
[Bug] RuntimeRrror: Ninja is required to load c++ extensions
#2514 opened Dec 19, 2024 by Flynn-Zh
2 of 5 tasks
1
[Feature] Support for Evicting Specific KV Cache to Save GPU Memory
#2510 opened Dec 18, 2024 by ChenlongDeng
2 tasks done
[Feature] do sample = False?
#2508 opened Dec 18, 2024 by boqiny
2 tasks done
[Feature] TORCHINDUCTOR_CACHE_DIR not work ?
#2507 opened Dec 18, 2024 by MichoChan
2 tasks done
1
[Feature] Integration SGLang into OpenRLHF collaboration high priority
#2506 opened Dec 17, 2024 by zhaochenyang20
2 tasks done
@zhaochenyang20
[Feature] Add Tutorial for Constraint Decoding documentation Improvements or additions to documentation good first issue Good for newcomers
#2505 opened Dec 17, 2024 by zhaochenyang20
2 tasks done
@zhaochenyang20
[Feature] Add Math in our CI enhancement New feature or request good first issue Good for newcomers
#2504 opened Dec 17, 2024 by zhaochenyang20
2 tasks
@zhaochenyang20
[Feature] Benchmarking Performance on General Devices collaboration enhancement New feature or request
#2488 opened Dec 16, 2024 by zhaochenyang20
2 tasks done
@zhaochenyang20
[Feature] request smoothquant (int8, W8A8) quantization on 40G A100
#2474 opened Dec 13, 2024 by Hao-YunDeng
2 tasks done
@ispobock @HandH1998
5
[Feature] Integrate CUTLASS FP8 GEMM into sgl-kernel high priority performance quant LLM Quantization
#2472 opened Dec 12, 2024 by zhyncs
2 tasks
@HaiShaw @HandH1998 @zhyncs
3
[Feature] FusedMoE H200 tuning enhancement New feature or request
#2471 opened Dec 12, 2024 by zhyncs
2 tasks
@zhyncs
[Bug] Different behavior benchmarking w/ request-range-range vs. separate request-rates
#2470 opened Dec 12, 2024 by Mutinifni
5 tasks done
@ispobock @zhyncs
1
"GET / HTTP/1.1" 404 Not Found
#2468 opened Dec 12, 2024 by LordEdison
2
[Feature] Do we have any plan for supporting MiniCPM-V 2.6? collaboration
#2461 opened Dec 12, 2024 by Xeladoes
2 tasks done
@zhaochenyang20
1
[Bug] CUDA Graph Build Failure
#2460 opened Dec 12, 2024 by dangxingyu
5 tasks done
[Bug] Gemma 2 GGUF
#2451 opened Dec 11, 2024 by slivka83
5 tasks done
[Feature]: Benchmarking H200 good first issue Good for newcomers high priority
#2450 opened Dec 11, 2024 by antferdom
2 tasks done
@zhyncs
6
It's hard to install it
#2445 opened Dec 11, 2024 by ToSev7en
2
ProTip! Follow long discussions with comments:>50.