Popular repositories Loading

1. vllm.xpu vllm.xpu Public

   vLLM on Intel Arc 140V (Lunar Lake): Tiel-Coder MoE serving at 27 tok/s, EXL3 2.2/4.0bpw port with no-DPAS + mixed-K patches, MTP/spec-decoding, perplexity and quality benchmarks

   Python 1

2. labtool labtool Public

   Forked from embeddedartists/labtool

   Software for the LabTool logic analyzer and oscilloscope

   C

3. Pake Pake Public

   Forked from tw93/Pake

   🤱🏻 Turn any webpage into a desktop app with one command.

   Rust

4. AInfer AInfer Public

   C

5. llama.cpp-arc-140v llama.cpp-arc-140v Public

   llama.cpp with Intel Arc 140V (Lunar Lake) adaptation: SYCL without Xe2 DPAS builtins, Vulkan ternary weight cache, 140V server launcher

   C++

6. EXL3_Intel_Arc_quantizer EXL3_Intel_Arc_quantizer Public

   EXL3 quantization and model conversion pipeline port to Intel Arc GPUs (SYCL / oneAPI / PyTorch XPU)

   Python