Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, 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, GraphRAG, DeepSpeed, Axolotl, etc
active 2024-03-25 → 2025-01-23 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 305 days from 2024-03-25 to 2025-01-23. Pushes: 1,656 total, peak 34 in a day. Pull requests: 3,141 total, peak 53 in a day. Issues: 792 total, peak 12 in a day. Comments: 3,782 total, peak 47 in a day. Stars: 2,075 total, peak 239 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Oscilloscope98 | 1.6K | 312 | 452 | 397 |
| rnwang04 | 1.2K | 139 | 247 | 319 |
| MeouSker77 | 862 | 213 | 435 | 95 |
| plusbang | 707 | 106 | 201 | 163 |
| liu-shaojun | 680 | 237 | 263 | 77 |
| jason-dai | 618 | 41 | 73 | 251 |
| hkvision | 535 | 58 | 92 | 179 |
| gc-fu | 367 | 79 | 114 | 103 |
| cyita | 361 | 63 | 122 | 81 |
| qiyuangong | 342 | 39 | 79 | 132 |
| sgwhat | 340 | 31 | 66 | 193 |
| glorysdj | 315 | 10 | 13 | 99 |
| xiangyuT | 273 | 42 | 88 | 61 |
| qiuxin2012 | 270 | 30 | 59 | 144 |
| hzjane | 256 | 54 | 113 | 57 |
| shane-huang | 202 | 50 | 73 | 32 |
| lalalapotter | 183 | 21 | 41 | 63 |
| Uxito-Ada | 155 | 25 | 53 | 48 |
| leonardozcm | 137 | 24 | 49 | 47 |
| jenniew | 120 | 14 | 38 | 44 |
Recent activity
Latest issues, pull requests and releases
- Issue#12740rgov2025-01-23 21:11Build, rather than download, dependencies
- Issue comment#12739rgov2025-01-23 19:18Crash on AVX instruction on Gemini Lake
- Issue#12739rgov2025-01-23 10:02Crash on AVX instruction on Gemini Lake
- Issue comment#12737jason-dai2025-01-23 09:34Cline on vllm
- Pull request#12738Oscilloscope982025-01-23 09:25
- Pull request#12738Oscilloscope982025-01-23 09:20
- Issue comment#12736plusbang2025-01-23 08:21vpux-compiler error occured when using qwen2.5-7B in large content or prompt
- Issue#12737YongZhuIntel2025-01-23 07:56Cline on vllm
- Issue comment#12736dockerg2025-01-23 03:18vpux-compiler error occured when using qwen2.5-7B in large content or prompt
- Issue comment#12736plusbang2025-01-23 02:47vpux-compiler error occured when using qwen2.5-7B in large content or prompt
- Pull request#12734Oscilloscope982025-01-22 09:22
- Pull request#12735Oscilloscope982025-01-22 09:20
- Pull request#12734Oscilloscope982025-01-22 08:09
- Issue#12733HumerousGorgon2025-01-22 07:49Using Tensor Parallel in the ipex-llm-serving-xpu Docker Image results in a crash.
- Issue#12704qiuxin20122025-01-22 07:40[ipex-llm[cpp]][ollama][MTL iGfx] The GLM4:9b model produced erroneous output starting from the second inference
- Pull request#12728xiangyuT2025-01-22 07:03
- Issue#12732windedge2025-01-22 06:13deepseek
- Issue#12732windedge2025-01-22 06:12deepseek
- Pull request#12729rnwang042025-01-22 01:59
- Pull request#12731MeouSker772025-01-22 01:41
- Issue comment#12723xiangyuT2025-01-22 01:35non-stream is not supported
- Pull request#12730jason-dai2025-01-22 00:43
- Pull request#12730jason-dai2025-01-22 00:42
- Pull request#12729rnwang042025-01-21 11:03
- Pull request#12728xiangyuT2025-01-21 10:32
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 2,075 stars here means stars gained during the window, not the repo's star count.