Intel and RadixArk Partner to Optimize Open-Source SGLang Inference Stack

Intel Corporation announced a collaboration with RadixArk to optimize SGLang, an open-source AI inference stack, for Intel platforms, aiming to help developers and enterprises deploy AI models more efficiently and cost-effectively. Business Wire published the announcement on November 12, 2026.

How the SGLang Work Targets Intel Hardware

The collaboration covers Intel CPUs, GPUs and accelerators, including Intel Advanced Matrix Extensions (Intel AMX). Intel said the work is meant to give model builders and software engineers standard, open frameworks and interfaces while using Intel's compute density and built-in hardware acceleration. Developers gain faster time-to-production, reduced latency and flexible deployment options across existing data center and cloud capacity, according to the announcement.

Anil Nanduri, vice president, AI Products & GTM, Intel Data Center Group, said: "This collaboration ensures developers have Day-0 readiness and high-performance inference software directly optimized for Intel CPUs, GPUs and accelerators with an open approach and gives them the freedom to choose the tools, frameworks and technologies that best fit their needs."

Ying Sheng, CEO of RadixArk, said: "By upstreaming deep optimizations into the core framework, we are eliminating constraints and ensuring developers never have to compromise between open standards and high performance." Intel said the contributions go directly into community software rather than being treated as separate deployment decisions.

Intel's Recent Partnership Record

Intel's partnership record includes a June 2026 agreement with Apple for custom chip design and manufacturing in the United States, with volume production targeted for late 2027 or early 2028, according to akta.pro company records. The same records show Intel raised its Intel Foundry order pipeline to $15 billion, with Microsoft confirmed as a custom chip customer and Google selected for half of TPU production through 2028 on the $55 billion Terafab project. In December 2025, NVIDIA completed a $5 billion private placement in Intel, acquiring 214.8 million shares at $23.28 per share and committing to co-develop PC and data center processors.

Earlier Intel Platform Announcements

On November 11, 2026, DIGITIMES Asia reported that Intel is expanding its CPU and GPU portfolio with the Intel GPU D-series, code-named Crescent Island, and next-generation Xeon processors, code-named Diamond Rapids, targeting large-model inference and enterprise high-performance orchestration workloads. The same outlet reported that Intel is expanding its 18A reach with the Intel Core Series 3 processor, code-named Wildcat Lake, for mainstream consumer and commercial notebooks. Also on November 11, 2026, Prtimes reported that Cyberlink optimized its FaceMe SDK for Intel Core Ultra processors, using the iGPU and OpenVINO to boost face recognition speed.