Skip to content

Issues: lmstudio-ai/lmstudio-bug-tracker

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

343 Open 124 Closed
343 Open 124 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

HF_ENDPOINT is not used when downloading modes.
#474 opened Mar 3, 2025 by liudonghua123
1
Markdown rendering of \( and \) is broken
#472 opened Mar 1, 2025 by avtc
Windows CUDA exit code 18446744072635812000
#471 opened Feb 28, 2025 by neilmehta24
4
support for rerank model
#470 opened Feb 28, 2025 by joebnb
Visual recognition function cannot be used when using Qwen2.5-VL
#469 opened Feb 28, 2025 by trainliang
Fixed error loading of VL class models
#468 opened Feb 28, 2025 by trainliang
Add support for "control" messages for Granite 3.2
#467 opened Feb 27, 2025 by pwilkin
Wan 2.0 loading error Unsupported Model
#466 opened Feb 27, 2025 by SkillfulElectro
please support strftime_now fixed-in-next-update Will work in the next version of the software
#465 opened Feb 27, 2025 by phazei
1
Failed to find image for token at index XXX for Qwen2-VL-7B more-info-needed Need more information to diagnose the problem
#464 opened Feb 27, 2025 by jsoma
5
embedding api request in parallelize cause crash needs-investigation
#463 opened Feb 25, 2025 by joebnb
7
Add conformation if i want to delete a message enhancement New feature or request
#459 opened Feb 23, 2025 by ehjr5u
1
Speculative Decoding slow: Doesn't prioritize offloading Draft model to GPU
#458 opened Feb 23, 2025 by deftdawg
LM Studio Won't Open
#455 opened Feb 22, 2025 by AnimeRyan-Official
IQ4_XS model not loading into VRAM
#454 opened Feb 21, 2025 by ghost
3
LM studio not ignoring tool call blocks within <think> tags needs-investigation
#453 opened Feb 21, 2025 by ghhwer
@mattjcly
1
Unable to index a custom fine-tuned model
#452 opened Feb 21, 2025 by ClixVG
Unable to index MLX models on external drive of Mac M3 - Same drive and models work on mlx-engine separately
#451 opened Feb 20, 2025 by nppyro
1
Nvidia Optimus Laptops. LM Studio at idle(with unloaded models) prevents the discrete GPU from entering power saving mode needs-investigation
#450 opened Feb 20, 2025 by ThatUsernameAlreadyExist
"Failed to index the following folder:"
#449 opened Feb 20, 2025 by christopherhastings
1
Mac High CPU/low quality when returning JSON via API
#448 opened Feb 20, 2025 by doublesharp
Error when Retrieving relevant citations for user query (almost the same as bug #438, but slightly different)
#446 opened Feb 19, 2025 by atelenga
the VL model encountered a 113 problem
#444 opened Feb 18, 2025 by bent2685
Not-useful error message when CORS disabled but required needs-investigation
#443 opened Feb 17, 2025 by abrenneke
4
Error running speculative inference more-info-needed Need more information to diagnose the problem
#441 opened Feb 17, 2025 by pwilkin
6
ProTip! Find all open issues with in progress development work with linked:pr.