Skip to content

Issues: mlc-ai/web-llm

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
75 Open 241 Closed
75 Open 241 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

Phi-3.5-vision-instruct-q4f16_1-MLC
#640 opened Nov 27, 2024 by raulgupta updated Dec 9, 2024
2
WebLLM always processes on Intel UHD Graphics, not on NVIDIA T1200
#609 opened Oct 10, 2024 by b521f771d8991e6f1d8e65ae05a8d783 updated Dec 4, 2024
9
New error: DXGI_ERROR_DEVICE_HUNG (0x887A0006)
#489 opened Jun 24, 2024 by time2bot updated Dec 3, 2024
2
Some questions regarding the WebLLM tool
#639 opened Nov 27, 2024 by jasonsu123 updated Dec 2, 2024
4
Error: Cannot initialize runtime because of requested maxComputeWorkgroupStorageSize exceeds limit. requested=32768, limit=16384.
#644 opened Nov 29, 2024 by badduck32 updated Nov 29, 2024
Hosting model on own webserver - relative paths in myAppConfig?
#294 opened Feb 11, 2024 by flatsiedatsie updated Nov 28, 2024
2
Trying to use the CreateServiceWorkerMLCEngine using Vite project but it doesn't work
#641 opened Nov 27, 2024 by v7Chord updated Nov 27, 2024
1
Is it possible to store a loaded engine in react to avoid multiple reloads when refreshing the app?
#636 opened Nov 22, 2024 by jvjmarinello updated Nov 26, 2024
2
Embedding load failing
#638 opened Nov 25, 2024 by djaffer updated Nov 25, 2024
Compiling Custom Model Fails to Load Into Web-LLM
#633 opened Nov 21, 2024 by Justin-Cignal updated Nov 22, 2024
Direct BNF support
#634 opened Nov 22, 2024 by Bainainai updated Nov 22, 2024
1
Transitive dependency of @webgpu/types for Typescript.
#631 opened Nov 17, 2024 by erikh2000 updated Nov 17, 2024
1
Loading LLM inside Electron window is very slow at the Compiling GPU Shader on Windows
#621 opened Oct 30, 2024 by StevenHanbyWilliams updated Nov 17, 2024
2
Use q3f16 models
#630 opened Nov 16, 2024 by bil-ash updated Nov 16, 2024
Structured JSON Generation
#629 opened Nov 13, 2024 by AvivSham updated Nov 15, 2024
1
Support for llama3.2-vision?
#625 opened Nov 7, 2024 by tgirotto updated Nov 7, 2024
Engine not instantiating for WebWorker bug Something isn't working
#394 opened May 13, 2024 by kitzj updated Nov 6, 2024
1
Service worker engine hangs forever if client is lost while streaming results
#620 opened Oct 26, 2024 by Bainainai updated Oct 28, 2024
@Neet-Nestor
Add Input Field for Custom Font Value Alongside Slider
#604 opened Oct 7, 2024 by Mefisto04 updated Oct 26, 2024
5
Revamp Navbar and Footer for Improved UI
#605 opened Oct 7, 2024 by Mefisto04 updated Oct 26, 2024
4
Save/restore intermediary state for prompt caching
#619 opened Oct 19, 2024 by Bainainai updated Oct 19, 2024
[FEATURE REQUEST] Add support for NPUs?
#612 opened Oct 12, 2024 by Iternal-JBH4 updated Oct 16, 2024
1
Introducing: papeg.ai
#608 opened Oct 10, 2024 by flatsiedatsie updated Oct 14, 2024
2
MLX engine support
#611 opened Oct 11, 2024 by onderceylan updated Oct 12, 2024
webLLMGlobal reference
#585 opened Sep 29, 2024 by lestan updated Oct 10, 2024
2
ProTip! Exclude everything labeled bug with -label:bug.