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 6
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

164 Open 114 Closed
164 Open 114 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

Is it possible to define the prompts for KV caching up-front?
#401 opened Apr 29, 2024 by timothylimyl
1
Support InternVL 1.5
#398 opened Apr 26, 2024 by themrzmaster
2
Prefill out of memory occur when deployed with servers
#393 opened Apr 25, 2024 by for-just-we
6
vLLM import error
#391 opened Apr 24, 2024 by jlin816
6
Regenerate benchmark results for latest vLLM
#389 opened Apr 24, 2024 by nilesh-c
1
Logprobs are almost the same for all choices
#388 opened Apr 23, 2024 by tom-doerr
8
Switch to non gated models
#387 opened Apr 23, 2024 by tom-doerr
1
ImportError: cannot import name 'get_cuda_stream' from 'triton.runtime.jit' In triton-nightly(V100)
#383 opened Apr 23, 2024 by nenomigami
How does or does sglang support multiple completions / samples given the same prompt?
#379 opened Apr 22, 2024 by wenting-zhao
Loading Chat Template in a more flexible way? good first issue Good for newcomers
#376 opened Apr 21, 2024 by for-just-we
Loading a BNB 4 bit model + adapter
#374 opened Apr 19, 2024 by timothelaborie
1
VLLM version high priority
#373 opened Apr 19, 2024 by eaubin
3
JSON decoding result don't match regex
#371 opened Apr 17, 2024 by DouHappy
Inference does not work in sglang with regex? bug Something isn't working
#361 opened Apr 11, 2024 by randomcodelookup
About parameter max_tokens
#360 opened Apr 11, 2024 by for-just-we
3
Don't get API response when sending images
#357 opened Apr 9, 2024 by tom-doerr
1
compatibility issues and memory leak problems --enable-flashinfer
#356 opened Apr 9, 2024 by pj-ml
3
Beam Search Support enhancement New feature or request
#353 opened Apr 8, 2024 by LiquidGunay
Beginner here, how to load the model from checkpoint
#349 opened Apr 5, 2024 by HoqueMahmudul
1
Potential Bug? Confusion about "need_vision" in llava implementation
#341 opened Apr 1, 2024 by fedshyvtest
Add Default Timeout to urllib.request.urlopen Calls to Prevent Potential Hanging
#339 opened Mar 29, 2024 by alessiodallapiazza
2
will support multi-loras inference？
#334 opened Mar 28, 2024 by skykiseki
Allow OPTIONS Method on Http Server and add Cors headers.
#333 opened Mar 28, 2024 by kseyhan
2
[Bug] llava-v1.6-34b can not enable Tensor Parallelism, server can not start
#330 opened Mar 25, 2024 by lss15151161
1
Supports the InternVL multimodal large model
#328 opened Mar 24, 2024 by exceedzhang
2
ProTip! Find all open issues with in progress development work with linked:pr.