{"full_name":"intel/ipex-llm","owner":"intel","name":"ipex-llm","shard":"1","url":"https://github.com/intel/ipex-llm","description":"Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.","homepage":"","topics":["pytorch","llm","transformers","gpu"],"tag_pages":["gpu","llm","pytorch","transformers"],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/17888862?v=4","created_at":"2016-08-29T07:59:50Z","pushed_at":"2026-01-28T17:32:40Z","metrics":{"stars":8841,"forks":1432,"watchers":8,"issues":3024,"prs":10285,"releases":22,"issues_open":1214,"issues_closed":1810,"prs_open":271,"prs_closed":1049,"prs_merged":8965,"discussions":2},"growth":{"day":{"stars":-1,"forks":0,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[8841,8841,8841,8841,8842,8842,8841],"forks":[1433,1433,1433,1433,1433,1432,1432],"watchers":[null,8,8,8,8,8,8],"issues_open":[null,1214,1214,1214,1214,1214,1214],"prs_open":[null,271,271,271,271,271,271]},"boards":{},"same_owner":[{"full_name":"intel/intel-one-mono","name":"intel-one-mono","shard":"1","boards":{}}],"issues":[{"number":12963,"title":"Support for gemma3 from google","comments":62,"created_at":"2025-03-12T14:29:08Z"},{"number":12844,"title":"Ollama can't run on 9th gen intel CPU or older, please use a newer version of Ollama","comments":39,"created_at":"2025-02-18T08:41:05Z"},{"number":13173,"title":"A770 Performance Issue with INT4","comments":37,"created_at":"2025-05-21T08:59:38Z"},{"number":12248,"title":"Brave Leo AI using Ollama and Intel GPU","comments":35,"created_at":"2024-10-23T05:32:25Z"},{"number":12723,"title":"non-stream is not supported","comments":33,"created_at":"2025-01-20T09:13:50Z"},{"number":13010,"title":"Unable to use GLM model","comments":30,"created_at":"2025-03-26T08:58:02Z"},{"number":13245,"title":"gemma3n unable to run ipex-llm","comments":26,"created_at":"2025-06-30T14:32:00Z"},{"number":11400,"title":" Native API returns: -2 (PI_ERROR_DEVICE_NOT_AVAILABLE)","comments":26,"created_at":"2024-06-22T12:35:48Z"}],"discussions":[{"number":11138,"title":"Support for max_loaded_maps and num_parallel variables/parameters","comments":1,"category":"General","created_at":"2024-05-26T02:17:38Z"},{"number":10258,"title":"What are the relationship and differences between bigdl and openvino?","comments":0,"category":"General","created_at":"2024-02-27T08:00:38Z"}],"latest_release":{"name":"IPEX-LLM release 2.2.0","tag":"v2.2.0","published_at":"2025-04-07T07:23:54Z","body":"## Highlights\r\n***Note:*** IPEX-LLM v2.2.0 has been updated to include functional and security updates. Users should update to the latest version.\r\n\r\nPlease go to https://github.com/ipex-llm/ipex-llm/releases/tag/v2.2.0 for the downloads.\r\n\r\n\r\n\r\n","is_prerelease":false},"readme":true,"readme_zh":true,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}