Skip to content

Issues: sgl-project/sglang

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

60 Open 545 Closed
60 Open 545 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]Support Qwen2_5...etc tools calling by OpenAI API
#1912 opened Nov 4, 2024 by CedricHwong
1 of 2 tasks
Expose max_total_num_tokens for Token Limit Calculation in Request Handling
#1900 opened Nov 3, 2024 by hahmad2008
1 of 5 tasks
1
Difference between TokenizerManager and Runtime class
#1898 opened Nov 3, 2024 by NrKhader
1
QWen VL Follow-up Fixes
#1897 opened Nov 3, 2024 by merrymercy
@yizhang2077
Benchmark torchao and torch.compile (need torch 2.5)
#1874 opened Nov 2, 2024 by jerryzh168
2
[Bug] Offline engine performance is not better than local server when running batch
#1872 opened Nov 1, 2024 by jischein
5 tasks done
@ByronHsu
Question: Does sglang support prefix cache for multimodal models?
#1870 opened Nov 1, 2024 by htrekker
Unable to Load Gemma2 Model with SGLANG
#1869 opened Nov 1, 2024 by hahmad2008
1 of 5 tasks
1
[Feature] Create a benchmark script for offline inference
#1865 opened Nov 1, 2024 by ByronHsu
@ByronHsu
1
TP8 scheduling overhead is very high for small model, Llama 3 8B
#1857 opened Oct 31, 2024 by hliuca
5 tasks done
8
Questions Regarding sglang vs vllm and Memory Management
#1828 opened Oct 28, 2024 by hahmad2008
1 of 5 tasks
3
[Feature] Support QLoRA weights enhancement New feature or request
#1826 opened Oct 28, 2024 by zzh-www
@Ying1123
2
[Bug] Got error with awq_marlin quantization args.
#1792 opened Oct 25, 2024 by liangzelang
5 tasks done
[Bug] cutlass group_gemm.initialize failed
#1788 opened Oct 25, 2024 by senlice
1 of 5 tasks
1
[Feature] Request to 8-bit Quantization of Attention with SageAttention good first issue Good for newcomers
#1763 opened Oct 23, 2024 by Snowdar
2 tasks done
1
[Feature] Multi options
#1761 opened Oct 23, 2024 by QinghanLai
2 tasks
4
[Feature] Cache-aware Data Parallel Router feature
#1732 opened Oct 20, 2024 by ByronHsu
@ByronHsu
[Bug][minimal reproducible demo] High variability across batch inference runs bug Something isn't working
#1729 opened Oct 20, 2024 by FredericOdermatt
5 tasks done
@Ying1123 @merrymercy @hnyls2002
5
[Feature] Cascade attention kernels good first issue Good for newcomers
#1715 opened Oct 19, 2024 by merrymercy
2
[Bug] crash about c10d::ProcessGroupNCCL::WorkNCCL::checkTimeout
#1693 opened Oct 17, 2024 by zeng-zc
5 tasks
2
[Feature] Make vLLM optional in model code wip
#1673 opened Oct 15, 2024 by ByronHsu
3 of 5 tasks
@ByronHsu @yizhang2077 @zhyncs
[Feature] When will a version of S-Lora be available?
#1668 opened Oct 14, 2024 by kunkunzhang123
2 tasks done
@Ying1123
1
[Feature] Multi-instance deployment
#1649 opened Oct 12, 2024 by vkc1vk
2 tasks done
@ByronHsu
3
[Feature] Using frontend APIs but passing a list of prompts in run rather than run_batch
#1624 opened Oct 10, 2024 by pengye91
2 tasks done
3
[Feature] GGUF support
#1616 opened Oct 9, 2024 by remixer-dec
2 tasks done
2
ProTip! Find all open issues with in progress development work with linked:pr.