Skip to content

Issues: intel/ipex-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

1,064 Open 1,688 Closed
1,064 Open 1,688 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

Alpaca QLoRA training doesn't support Gemma model
#12865 opened Feb 20, 2025 by vishakh15nair
unsupported SPIR-V version number 'unknown (66560)'
#12864 opened Feb 20, 2025 by lightgao
failed to load llama-3.2-vision using ollama-0.5.4-ipex-llm-2.2.0b20250218-win.zip
#12861 opened Feb 20, 2025 by fanlessfan
@sgwhat
2
Model just prints the same amount of "G"s user issue
#12859 opened Feb 20, 2025 by stereomato
3
No Qwen2.5-VL-7B-Instruct 4bit support user issue
#12858 opened Feb 20, 2025 by aixiwangintel
glm-4v, A770, got error " RuntimeError: probability tensor contains either inf, nan or element < 0" user issue
#12857 opened Feb 20, 2025 by aixiwangintel
@qiuxin2012
2
qwen2-vl, A770 GPU, got an unexpected keyword argument 'position_embeddings' error user issue
#12856 opened Feb 20, 2025 by aixiwangintel
2
2 x A770 with Ollama Linux , inference responses slow down dramatically user issue
#12852 opened Feb 19, 2025 by RobinJing
@sgwhat
[SOLVED] How to use IPEX-LLM with a VS Code Extension on Win10 ?
#12851 opened Feb 19, 2025 by redo33
Feature Request: Implementing a No-Install Runtime Package for Ollama on Intel NPU using IPEX-LLM
#12848 opened Feb 19, 2025 by ChenZeiShuai
docker: a770: ollama crashes
#12845 opened Feb 18, 2025 by tkatila
@sgwhat
4
Ollama can't run on 9th gen intel CPU or older, please use a newer version of Ollama
#12844 opened Feb 18, 2025 by Ejo2001
5
With Intel chips, how to fine-tune models with LoRA and use it on inference?
#12842 opened Feb 18, 2025 by JamieVC
1
To many memory using when using utlra 200V's npu
#12841 opened Feb 18, 2025 by shichang00
5
ollama + deepseek v2: The number of work-items in each dimension of a work-group cannot exceed {512, 512, 512} for this device user issue
#12839 opened Feb 17, 2025 by stereomato
2
[ipex-llm][cpp][ollama]nonsense output when running infer simultaneously (OLLAMA_NUM_PARALLEL!=1) user issue
#12835 opened Feb 17, 2025 by jianjungu
@sgwhat
Ollama reports model is 100% on CPU when actually running on GPU user issue
#12831 opened Feb 16, 2025 by tsobczynski
1
Lunar Lake Core Ultra 7 258V running docker container : intelanalytics/ipex-llm-inference-cpp-xpu:latest on Windows 11 , can not find preferred GPU platform fails user issue
#12830 opened Feb 14, 2025 by shailesh837
1
IGPU limits the inference speed of the entire system user issue
#12828 opened Feb 14, 2025 by dttprofessor
5
deepseek-v3 needs ollama 0.5.5 user issue
#12827 opened Feb 14, 2025 by stereomato
@sgwhat
1
Baichuan-M1-14B can save int4 model, but load low bit failed. user issue
#12824 opened Feb 14, 2025 by KiwiHana
Multivariate forecasting using Chronos
#12818 opened Feb 12, 2025 by asfand-khan-98
1
The latest driver 32.0.101.6559 broke inference speed
#12806 opened Feb 11, 2025 by xyang2013
6
Support for Hybrid Acceleration on CPU, GPU, and NPU
#12799 opened Feb 10, 2025 by Ursue
1
[Enhanced] Better Intel ARC GPU Docker user issue
#12795 opened Feb 10, 2025 by soulteary
@liu-shaojun
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.