dpas

Here is 1 public repository matching this topic...

Native Intel Xe2 LLM inference: SYCL/DPAS kernels, paged KV, prefix caching, continuous batching, and XMX packed prefill

intel sycl xe2 oneapi level-zero xmx intel-xpu intel-arc llm-inference qwen paged-attention dpas continuous-batching openai-compatible prefix-caching

To associate your repository with the dpas topic, visit your repo's landing page and select "manage topics."