For the previous three years, SGLang, an open-source venture, has processed trillions of tokens day by day for firms corresponding to Google, Microsoft, xAI, and Nvidia. Till not too long ago, most individuals outdoors the inference group didn’t know who created it.
RadixArk, a Palo Alto startup bringing SGLang to market, simply raised $100 million in seed funding at a $400 million valuation. The spherical was led by Accel and Spark Capital, with NVentures, Salience Capital, A&E Funding, HOF Capital, Walden Catalyst, AMD, LDVP, WTT Fubon Household, MediaTek, and Databricks becoming a member of
Different buyers embody John Schulman, co-founder of OpenAI; Soumith Chintala, creator of PyTorch; and Thomas Wolf, co-founder of Hugging Face. The CEOs of Intel and Broadcom additionally joined the spherical.
RadixArk was based by Ying Sheng and Banghua Zhu in 2025. Sheng constructed inference techniques for Elon Musk’s Grok fashions at xAI, and Zhu labored on techniques at Nvidia. In 2023, Sheng and he group created SGLang as a part of LMSYS analysis group, a non-profit created by researchers from Stanford, Berkeley, CMU, UCSD, amongst others.
SGLang turned standard within the inference group due to its technical strengths, with none advertising or gross sales group. At this time, it runs on a whole bunch of 1000’s of GPUs. Its primary competitor is vLLM, one other open-source engine from Berkeley that additionally become a funded startup.
SGLang solves a serious reminiscence drawback in AI inference. Normally, AI fashions recompute the context for every question, even when a lot of the immediate is identical. SGLang makes use of a Radix tree knowledge construction to retailer beforehand processed components, lowering redundant work for brand spanking new queries. This reduces the per-token computational price and helps organisations get monetary savings when operating their very own inference.
“Our mission is straightforward but formidable: make frontier-level AI infrastructure open and accessible to everybody. We imagine the following technology of AI gained’t be outlined by who owns the most important personal infrastructure, however by who builds essentially the most significant functions on prime of shared, world-class techniques. We purpose to make these techniques orders of magnitude cheaper and extra accessible, so everybody can construct on them,” says Sheng.
The effectivity is on the coronary heart of RadixArk’s mission. It retains SGLang open and free, however makes cash by providing managed internet hosting, just like what Databricks and Elastic do.
“RadixArk is constructing the open basis for the following period of AI — the place firms don’t simply eat fashions, they prepare and handle them as a core a part of product growth. By democratising coaching and inference infrastructure, RadixArk allows any engineer to experiment and innovate on the frontier, absolutely proudly owning how AI powers their merchandise,” notes Ivan Zhou, associate at Accel.
The brand new funding will assist RadixArk broaden to extra mannequin varieties and {hardware} and develop its managed platform.
