Jumbomuffin777 / XeMaya
Native inference for Intel Arc GPUs (SYCL / Level Zero, XMX): Qwen3.8-Flash-Next, GLM-5.3-Flash and DeepSeek-V4.1-Flash. Alpha. A fork of XeStrata, targeting Project Maya's models.
Why this job: topics: llm-inference, gguf
What it does
XeMaya is an Intel Arc-first inference engine for Qwen3.8-Flash-Next, GLM-5.3-Flash and DeepSeek-V4.1-Flash. It runs native SYCL / Level Zero kernels, including Intel XMX paths, with multi-GPU layer splitting and VRAM / RAM / SSD expert tiers. The engine is built on XeStrata, rather than a llama.cpp server wrapper or a CUDA compatibility layer.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit yesterday
- Stars
- 11
- On GitHub
- Licence
- LGPL-3.0
- Share-alike for changes
- Downloads for
- Linux
- From the latest release
- Latest tag
- xemaya-0.1.0-alpha.2
- Released yesterday
- Built with
- C++
- 66% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 1 merged
- 0 waiting
- Releases
- 2
- 2 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
More: download files, languages, topics and project record
Languages
- C++ 66%
- Python 30%
- JavaScript 2%
- CMake 1%
Topics
- gguf
- intel-arc
- level-zero
- llm-inference
- sycl
Project record
- JobLocal LLMs
- StatusNew to our list
- Commits7,933
- Forks4
- Watching0
- CreatedNov 10, 2026
- First seen by usNov 11, 2026
- CheckedNov 12, 2026