Skip to content

Issues: intel/ipex-llm

Beta
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

1,146 Open 1,745 Closed
1,146 Open 1,745 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

Tensor parallel vllm fails on eGPU user issue
#13131 opened May 3, 2025 by kirel
Llama.cpp portable fails to initialise with context sizes above 22528 (24 x 1024). user issue
#13130 opened May 3, 2025 by HumerousGorgon
Ollama for intel run qwen3(8b、14b、30b-a3b)slower than lm studio
#13128 opened May 1, 2025 by wrteww
2
Ollama on old cpu
#13127 opened May 1, 2025 by D1b4l4p
Instructions for Ollama Installation with IPEX on Multi-GPU Fail to Work with Arc GPU user issue
#13126 opened Apr 30, 2025 by Kaszanas
ImportError: cannot import name 'LoadLoraAdapterRequest' user issue
#13124 opened Apr 30, 2025 by kirel
3
gemma3 and qwen3
#13123 opened Apr 29, 2025 by ybeetle8
5
Error running ipex-llm user issue
#13122 opened Apr 29, 2025 by Njur
5
It is hoped that the qwen3 series models can be supported quickly
#13121 opened Apr 29, 2025 by brownplayer
2
IPv6 needs to be disabled before PPA install user issue
#13112 opened Apr 26, 2025 by dennis-george0
@Oscilloscope98
1
Can not replicate advertised performance on A770
#13110 opened Apr 25, 2025 by giancarlo-metitieri
1
[XPU] library mismatch and version issue while performing fine-tuning on B580 user issue
#13108 opened Apr 24, 2025 by raj-ritu17
@Uxito-Ada
3
Ollama failed to run deepseek-coder-v2,Error: unable to load model user issue
#13107 opened Apr 24, 2025 by weryswang
@qiuxin2012
1
Can't set Ollama context size - seems to be fixed to 8k user issue
#13106 opened Apr 24, 2025 by kirel
@sgwhat
3
Intel iGPU is not used user issue
#13105 opened Apr 24, 2025 by PharahAmari
@sgwhat
3
Does ipex-llm support AMX for decode?
#13102 opened Apr 23, 2025 by mapicccy
3
GLM-4-9B-0414 meet ValueError: The checkpoint you are trying to load has model type glm4 but Transformers does not recognize this architecture. user issue
#13100 opened Apr 21, 2025 by KiwiHana
3
[BUG] Run 8-bit and16-bit gemma3-4b user issue
#13099 opened Apr 21, 2025 by bibekyess
5
http://localhost:11434 cannot be accessed user issue
#13096 opened Apr 20, 2025 by RICHES-2020
@sgwhat
5
--verbose-prompt does not print any additional information user issue
#13090 opened Apr 17, 2025 by HanShengGoodWay
3
NPU inference sym_int4 model error
#13089 opened Apr 17, 2025 by Gusha-nye
Running ipex-llm harness on A770 failed. user issue
#13087 opened Apr 17, 2025 by tao-ov
5
Feature request - add support for the mojo lang and max platform
#13086 opened Apr 17, 2025 by NewtonChutney
Using the Speech_Paraformer-Large model reports an error OSError: [WinError -529697949] Windows Error 0xe06d7363 when running on NPU. user issue
#13083 opened Apr 16, 2025 by Bofuser
@hkvision
IPEX-LLM Slow Token Generation on Gemma 3 12B on Arc A770M user issue
#13080 opened Apr 15, 2025 by Sketchfellow
1
ProTip! Find all open issues with in progress development work with linked:pr.