Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #3453] [FEAT]: Please suppport Processor Intel Core Ultra 7 #2228

New Issue
Closed
opened 2026-02-22 18:28:45 -05:00 by yindo · 3 comments
yindo commented 2026-02-22 18:28:45 -05:00
Owner
Copy Link
Copy Source

Originally created by @kaiserwassser on GitHub (Mar 13, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3453

What would you like to see?

Please support the Intel Processor Intel Core Ultra 7 CPU beacuse it seems I have a NPU onboard but I cannot use it.

NPU Specifications

  • NPU Name‡Intel® AI Boost
  • NPU Peak TOPS (Int8) 13
  • Sparsity SupportYes
  • Windows Studio Effects SupportYes
  • AI Software Frameworks Supported by NPUOpenVINO™, WindowsML, DirectML, ONNX RT, WebNN

The NPU Accelaration library seems to be here:
https://github.com/intel/intel-npu-acceleration-library

Image

I tried but the NPU graph remains flat on Anything LLM :(

Originally created by @kaiserwassser on GitHub (Mar 13, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3453 ### What would you like to see? Please support the Intel Processor Intel Core Ultra 7 CPU beacuse it seems I have a NPU onboard but I cannot use it. **NPU Specifications** - NPU Name‡Intel® AI Boost - NPU Peak TOPS (Int8) 13 - Sparsity SupportYes - Windows Studio Effects SupportYes - AI Software Frameworks Supported by NPUOpenVINO™, WindowsML, DirectML, ONNX RT, WebNN The NPU Accelaration library seems to be here: https://github.com/intel/intel-npu-acceleration-library ![Image](https://github.com/user-attachments/assets/07e6e66c-fcbb-44e2-8f4d-84e7d3e5c1ce) I tried but the NPU graph remains flat on Anything LLM :(
yindo added the enhancementfeature request labels 2026-02-22 18:28:45 -05:00
yindo closed this issue 2026-02-22 18:28:45 -05:00
yindo commented 2026-02-22 18:28:45 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Mar 13, 2025):

We only currently have support for Snapdragon X NPU because they work with us and we had to build out own engine to do it because Ollama and LMStudio both dont support NPU models yet. The Snapdragon support was an exception, in general we do not build LLM inference engines since we need a machine to do so since every device's NPU has it's own support and SDK concerns.

@timothycarambat commented on GitHub (Mar 13, 2025): We only currently have support for Snapdragon X NPU because they work with us **and** we had to build out own engine to do it because Ollama and LMStudio both dont support NPU models yet. The Snapdragon support was an exception, in general we do not build LLM inference engines since we need a machine to do so since every device's NPU has it's own support and SDK concerns.
yindo commented 2026-02-22 18:28:45 -05:00
Author
Owner
Copy Link
Copy Source

@kaiserwassser commented on GitHub (Mar 14, 2025):

Ok so I have to open an issue to Ollama. Tkz I'll do !

@kaiserwassser commented on GitHub (Mar 14, 2025): Ok so I have to open an issue to Ollama. Tkz I'll do !
yindo commented 2026-02-22 18:28:45 -05:00
Author
Owner
Copy Link
Copy Source

@CrocodileCowboy commented on GitHub (May 10, 2025):

My system with a Intel Processor Intel Core Ultra 7 CPU also has a discrete Arc770. I use the intel ollama build and it either run on the GPU. It is worth a try.

TO use it with anythingllm, I need to start the intel version of Ollama first, load the right model and then start anythingllm.

https://github.com/ipex-llm/ipex-llm/releases/tag/v2.3.0-nightly

@CrocodileCowboy commented on GitHub (May 10, 2025): My system with a Intel Processor Intel Core Ultra 7 CPU also has a discrete Arc770. I use the intel ollama build and it either run on the GPU. It is worth a try. TO use it with anythingllm, I need to start the intel version of Ollama first, load the right model and then start anythingllm. https://github.com/ipex-llm/ipex-llm/releases/tag/v2.3.0-nightly
yindo changed title from [FEAT]: Please suppport Processor Intel Core Ultra 7 to [GH-ISSUE #3453] [FEAT]: Please suppport Processor Intel Core Ultra 7 2026-06-05 14:45:18 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label enhancement feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#2228
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?