-
Notifications
You must be signed in to change notification settings - Fork 180
Issues: sgl-project/sglang
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
OpenAI ChatCompletionRequest max_tokens defaults to None causing error
#582
by brandonbiggs
was closed Jul 9, 2024
[Bug] Truncated Decoding Output When Using Streamed Output with srt
#580
by Titan-p
was closed Jul 6, 2024
[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
missing 1 required positional argument: 'page_size' when using --enable-flashinfer
#565
by keepitsane
was closed Jun 26, 2024
Chinese Regex BUG in req.jump_forward_map.jump_forward_byte
#549
by wellhowtosay
was closed Jun 16, 2024
Seems only GPU 0 is being used even when in tensor parallel across 2 GPUs
#536
by aflah02
was closed Jun 13, 2024
AttributeError: module 'flashinfer' has no attribute 'batch_prefill_with_paged_kv_cache'
#533
by ZackZeng999
was closed Jun 26, 2024
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
Support for Qwen2MoeForCausalLM?
good first issue
Good for newcomers
#513
by fedshyvana
was closed Jul 9, 2024
llava http request hang when do set_default_backend(RuntimeEndpoint("http:https://ip:port"))
#497
by LetheRiver0
was closed Jun 3, 2024
consistently hitting FileNotFoundError for triton cache kernel stage
#472
by pseudotensor
was closed May 25, 2024
ValueError: Unsupported architectures: LlavaQwenForCausalLM
#467
by pseudotensor
was closed May 24, 2024
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.