Skip to content

Issues: sgl-project/sglang

Development Roadmap (2024 Q4)
#1487 opened Sep 21, 2024 by Ying1123
Open 8
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

62 Open 579 Closed
62 Open 579 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

[BUG] Problems with jump forward decoding grammar-backend
#2045 opened Nov 15, 2024 by merrymercy
[Bug] Qwen2VL Crashes on some inputs
#2037 opened Nov 14, 2024 by jakep-allenai
5 tasks done
@yizhang2077
[Feature] Support Qwen2-VL based embedding model good first issue Good for newcomers
#2032 opened Nov 14, 2024 by VoVAllen
2 tasks done
[BUG] Jump forward w/ outlines backend slightly changes the decoding results grammar-backend
#2025 opened Nov 13, 2024 by merrymercy
[BUG] xgrammar does not follow the constraint grammar-backend
#2017 opened Nov 12, 2024 by merrymercy
4
[Feature] Regex stop condition good first issue Good for newcomers
#2007 opened Nov 11, 2024 by SinanAkkoyun
2 tasks done
1
[Feature] Are there plans to support AWQ and torch compile?
#1991 opened Nov 11, 2024 by sitabulaixizawaluduo
2 tasks done
3
[Bug] how to combine with ray.data
#1987 opened Nov 10, 2024 by mdy666
1 of 5 tasks
2
[Feature] Throughput-aware speculative decoding
#1979 opened Nov 10, 2024 by vkc1vk
2 tasks done
1
[Feature] Is AWQ W4Afp8 supported?
#1964 opened Nov 8, 2024 by vkc1vk
2 tasks done
1
[Bug] amdgpu，tp-size=2，Detected errors during sampling! NaN in the logits. amd
#1953 opened Nov 8, 2024 by linqingxu
5 tasks done
4
[Bug] tp-size=2，model launch error amd
#1945 opened Nov 7, 2024 by linqingxu
5 tasks
3
[Feature] Add LoRA Support for Chat Completion in SGLang good first issue Good for newcomers
#1936 opened Nov 6, 2024 by mssongit
2 tasks done
[Feature] Save cache from requests and load good first issue Good for newcomers
#1932 opened Nov 6, 2024 by SinanAkkoyun
2 tasks done
1
[Bug] Incompatible with outlines>=0.1.0
#1930 opened Nov 5, 2024 by dzimmerman-nci
5 tasks done
3
[Bug] Get connection error when use sglang python module
#1927 opened Nov 5, 2024 by kanebay
[Bug] Torch 2.5 issue with Tensor Parallel Size > 1
#1925 opened Nov 5, 2024 by CortexEdgeUser
5 tasks done
1
[Bug] Launching a server with --enable-torch-compile produce torch dynamo error
#1923 opened Nov 5, 2024 by msublee
5 tasks done
6
[Bug] Make multi-lora serving compatible with cuda graph and radix cache help wanted Extra attention is needed
#1921 opened Nov 5, 2024 by LIUKAI0815
4 of 5 tasks
1
[Feature]Support Qwen2_5...etc tools calling by OpenAI API good first issue Good for newcomers
#1912 opened Nov 4, 2024 by CedricHwong
1 of 2 tasks
Expose max_total_num_tokens for Token Limit Calculation in Request Handling good first issue Good for newcomers
#1900 opened Nov 3, 2024 by hahmad2008
1 of 5 tasks
3
Benchmark torchao and torch.compile (need torch 2.5)
#1874 opened Nov 2, 2024 by jerryzh168
4
[Bug] Offline engine performance is not better than local server when running batch
#1872 opened Nov 1, 2024 by jischein
5 tasks done
@ByronHsu
2
TP8 scheduling overhead is very high for small model, Llama 3 8B on AMD amd
#1857 opened Oct 31, 2024 by hliuca
5 tasks done
9
Questions Regarding sglang vs vllm and Memory Management
#1828 opened Oct 28, 2024 by hahmad2008
1 of 5 tasks
3
ProTip! What’s not been updated in a month: updated:<2024-10-15.