RadixArk

Headlines · 5

1. Oct 23
   MiniMax M3.1 Flash adds SGLang and Miles integration

   MiniMax said MiniMax M3.1 Flash can run with SGLang for inference and reinforcement learning through Miles. The company claimed it exceeded 1,000 tokens per second for batch-size-1 decoding with SGLang and was production-ready from day one. The integration was described as a joint effort involving MiniMax, NVIDIA, AMD, and RadixArk, but the report included no independent throughput measurement.

   MiniMax_AI (X) · 🔥 0
2. Oct 20
   SGLang launches open-source PyTorch-native TPU serving backend

   SGLang launched SGLang-TorchTPU, an open-source native PyTorch backend that brings its serving stack to Google Cloud TPU while retaining the same core codebase used for GPUs. The project, developed by RadixArk’s SGLang team with Google and Meta, includes real-TPU CI tests and support for multiple language and diffusion models. SGLang and Meta personnel said the backend is running production inference at Meta, while Tom’s Hardware also reported the open-source release of a matching PyTorch-native vLLM version.

   LMSYS Blog · 🔥 0
3. Oct 20
   vLLM and SGLang launch native PyTorch backends for Google Cloud TPUs

   vLLM released vLLM TorchTPU, an out-of-tree platform plugin that lets vLLM run on Google Cloud TPUs, and Google said it also launched a native PyTorch backend for SGLang built with RadixArk. Both engines are built on Google's TorchTPU stack, reuse existing model definitions and keep upstream schedulers, KV cache managers and OpenAI-compatible servers, with TPU-specific Pallas kernels for attention, mixture-of-experts and quantized matmuls. Google says the engines are running in production with preview customers and cites SemiAnalysis InferenceX results including 2.01 cents per million tokens, while vLLM lists TPU v7x (Ironwood) as recommended hardware and v6e, v5e and v5p as experimental.

   vLLM Blog · 🔥 0
4. Oct 11
   AI infra spending boom meets idle GPUs at Beijing salon

   A closed-door salon on AI infrastructure hosted by Touzhongwang with Zhongguancun partners, republished by 36Kr, examined the gap between huge AI infrastructure spending and weak efficiency. It cites ByteDance's $29.6 billion syndicated loan, Alibaba's HK$80 billion placement, more than $80 billion raised earlier by Google and Amazon, and NVIDIA's $500 billion plan, while noting China's daily token calls topped 140 trillion in March, over a thousand times early-2024 levels. Participants cited a Carnegie Mellon test of 756 GPUs running 31 days with the cluster waiting nearly 20% of the time, claimed over half of OpenAI's inference energy goes to idle work, and said average GPU utilization at Chinese smart-computing centers is below 30%. Several investors called lowering token cost and raising utilization the new deciding factor; SGLang's RadixArk reportedly raised a $100 million seed at a $400 million valuation, while one dissenting view argued inference revenue will fall sharply as algorithms compress token use by orders of magnitude.

   36氪 人工智能 · 🔥 0
5. Oct 9
   Blog SGLang and Miles on NVIDIA Vera Rubin We had early access to two NVIDIA Vera Rubin nodes (8 GPUs) and used them to bring SGLang and Miles up on the platform: SGLang for inference and Miles for RL training. SGLang & Miles Team October 9, 2026

   On this page Summary Inference: Serving Kimi K3 NVFP4 Attention MoE and communication kernels KDA RL training: Miles on NVIDIA Vera Rubin Agentic RL on the Vera CPU What's Next Acknowledgements Summary We had early access to two NVIDIA Vera Rubin nodes (8 GPUs) and used them to bring SGLang and Miles up on the platform: SGLang for inference and Miles for RL training. On the inference side, we tuned SGLang for Kimi K3 NVFP4: this post covers what we changed in the attention, MoE/communication and KDA kernels, and how much each change bought. On the training side, Miles, which uses SG

   LMSYS Blog · 🔥 0

Experience and discussion from the community

Share my RadixArk experienceAsk about RadixArk