Skip to content

Issues: sgl-project/sglang

Development Roadmap (2024 Q4)
#1487 opened Sep 21, 2024 by Ying1123
Open 21
[Feature] DeepSeek V3 optimization
#2591 opened Dec 26, 2024 by zhyncs
Open 7
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

137 Open 668 Closed
137 Open 668 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] add AMD CIs amd
#2621 opened Dec 27, 2024 by zhyncs
2 tasks
@HaiShaw
[Feature] FlashInfer new version integration enhancement New feature or request flashinfer high priority
#2620 opened Dec 27, 2024 by zhyncs
2 tasks
@zhyncs
1
[Bug] Launching Llama-3.2-11B-Vision-Instruct just hangs on generation
#2619 opened Dec 27, 2024 by SuperMasterBlasterLaser
5 tasks done
1
[Bug] LLVM/Triton issue
#2613 opened Dec 27, 2024 by NilayYadav
5 tasks done
[Bug] OOM when setting return_logprob=True
#2607 opened Dec 27, 2024 by CSammyfd
5 tasks done
[torch.compile] Large cache size limit
#2604 opened Dec 26, 2024 by anijain2305
3
Use absolute paths in imports
#2602 opened Dec 26, 2024 by merrymercy
@yizhang2077 @zhyncs
[Bug] Cannot run bitsandbytes llama models good first issue Good for newcomers help wanted Extra attention is needed
#2600 opened Dec 26, 2024 by merrymercy
1
[Bug] tuning deepseek v2/v3 fused_moe_triton crashed.
#2599 opened Dec 26, 2024 by BBuf
5 tasks done
@BBuf
1
[Bug] Deepseek v3 doesn't work on mi300x
#2595 opened Dec 26, 2024 by ferrybaltimore
5 tasks done
1
[Feature] DeepSeek V3 optimization enhancement New feature or request high priority performance quant LLM Quantization
#2591 opened Dec 26, 2024 by zhyncs
5 of 15 tasks
@HaiShaw @Ying1123
@merrymercy @ispobock @HandH1998 @zhyncs
7
[Bug] libcudart.so.12: cannot open shared object file: No such file or directory
#2584 opened Dec 26, 2024 by githust66
5 tasks
8
[Feature] Proposal: Releasing SGLang memory when idle feature high priority
#2583 opened Dec 26, 2024 by fzyzcjy
@zhaochenyang20
10
[Feature] Request to Include flashinfer as a Dependency for sglang Installation dependencies Pull requests that update a dependency file high priority
#2578 opened Dec 25, 2024 by richardodliu
2 tasks done
@zhaochenyang20
3
[Feature] Due to GIL issues, the overlap mode doesn't actually always bring benefits?
#2573 opened Dec 25, 2024 by CSEEduanyu
2 tasks done
[Feature] (Willing to PR) Proposal: Drop-in fast replacement of PreTrainedModel.generate collaboration enhancement New feature or request feature high priority RLHF Using SGLang for post training
#2569 opened Dec 24, 2024 by fzyzcjy
2 tasks done
6
[Feature] Running multi-node offline engine inference ( via SLURM) collaboration feature help wanted Extra attention is needed
#2561 opened Dec 23, 2024 by aflah02
2 tasks done
@zhaochenyang20
23
lora speed enhancement New feature or request
#2559 opened Dec 23, 2024 by qingzhong1
@zhaochenyang20
1
[Feature] Improve the Zero-Overhead Batch Scheduler performance for the small model
#2558 opened Dec 23, 2024 by libratiger
2 tasks done
4
upgrade setuptools and wheel if you found "torch module not found" when installing bug Something isn't working
#2554 opened Dec 23, 2024 by MiladInk
@zhaochenyang20
1
[Bug] Outlines version error for Grammar Backend bug Something isn't working good first issue Good for newcomers
#2550 opened Dec 23, 2024 by zhaochenyang20
5 tasks done
@zhaochenyang20
5
[Feature] Set outlines and xgrammar as addtional dependency enhancement New feature or request grammar-backend
#2549 opened Dec 23, 2024 by zhaochenyang20
2 tasks done
@zhaochenyang20
3
[Feature] (Willing to PR) Avoid KV cache occupying GPU memory when not used collaboration feature high priority
#2542 opened Dec 22, 2024 by fzyzcjy
2 tasks done
@zhaochenyang20
27
[Bug] Eagle2 has an unstable sampling rate during multi concurrency。
#2537 opened Dec 21, 2024 by coolhok
5 tasks done
[Feature] Add Docs For Quantization good first issue Good for newcomers quant LLM Quantization
#2531 opened Dec 20, 2024 by binhtranmcs
@zhaochenyang20
4
ProTip! Find all open issues with in progress development work with linked:pr.