Skip to content

Issues: sgl-project/sglang

Development Roadmap
#157 opened Feb 7, 2024 by Ying1123
Open 14
Add SGLang usage examples
#166 opened Feb 8, 2024 by Ying1123
Open 7
Trouble Shooting
#548 opened Jun 14, 2024 by Ying1123
Open
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

Clear current search query, filters, and sorts
160 Open 126 Closed
160 Open 126 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

OpenAI ChatCompletionRequest max_tokens defaults to None causing error
#582 by brandonbiggs was closed Jul 9, 2024
1
@ChuyueSun
1
[Bug] Truncated Decoding Output When Using Streamed Output with srt
#580 by Titan-p was closed Jul 6, 2024
1
4
[Bug] forward() inferface of flashinfer has changed from version 0.0.6 to version 0.0.7
#575 by PanJason was closed Jul 2, 2024
1
Why using 16 bit dtype in memory pool state？
#570 by yileld was closed Jul 9, 2024
1
missing 1 required positional argument: 'page_size' when using --enable-flashinfer
#565 by keepitsane was closed Jun 26, 2024
4
[Model] Adding support for MiniCPM-Llama3-V-2_5
#562 by ssuncheol was closed Jun 25, 2024
Will speculative decoding be supported?
#555 by arunpatala was closed Jun 19, 2024
3
peer access is not supported between these two devices
#552 by gmonair was closed Jul 7, 2024
2
Chinese Regex BUG in req.jump_forward_map.jump_forward_byte
#549 by wellhowtosay was closed Jun 16, 2024
1
1
MoE model (BDRX/Mixtral) NaN when using flashinfer
#547 by Ying1123 was closed Jul 5, 2024
@Ying1123
1
Clarification for wait_for_new_request_delay changes
#541 by Qubitium was closed Jun 17, 2024
1
Seems only GPU 0 is being used even when in tensor parallel across 2 GPUs
#536 by aflah02 was closed Jun 13, 2024
4
AttributeError: module 'flashinfer' has no attribute 'batch_prefill_with_paged_kv_cache'
#533 by ZackZeng999 was closed Jun 26, 2024
@ZackZeng999
1
ImportError: cannot import name 'pin_program'
#532 by ZackZeng999 was closed Jun 30, 2024
1
@ZackZeng999
Access values created within a fork
#529 by brunorigal was closed Jun 12, 2024
2
Qwen 2 7B not working
#522 by sudarshan-kamath was closed Jun 10, 2024
2
Proxy keys should use proper URL forms rather than plain scheme strings. Instead of "localhost", use "localhost:https://"
#521 by dmilcevski was closed Jun 13, 2024
4
Support for Qwen2MoeForCausalLM? good first issue Good for newcomers
#513 by fedshyvana was closed Jul 9, 2024
2
Improving SG-LANG boot-times?
#509 by schopra8 was closed Jun 10, 2024
1
llava http request hang when do set_default_backend(RuntimeEndpoint("http:https://ip:port"))
#497 by LetheRiver0 was closed Jun 3, 2024
Rename variable names for rank
#482 by Ying1123 was closed Jun 8, 2024
@Ying1123
typo in sglang/srt/server.py Runtime log_evel
#478 by dhgarcia was closed Jul 1, 2024
1
consistently hitting FileNotFoundError for triton cache kernel stage
#472 by pseudotensor was closed May 25, 2024
3
ValueError: Unsupported architectures: LlavaQwenForCausalLM
#467 by pseudotensor was closed May 24, 2024
3
Invalid API key
#466 by pseudotensor was closed May 24, 2024
2
ProTip! Mix and match filters to narrow down what you’re looking for.