SGLang

Intel and RadixArk Optimize SGLang for Open AI Inference
Intel and RadixArk are collaborating to optimize SGLang, an open-source AI inference stack, for Intel platforms. The companies say the work aims to help developers and…

PyTorch team integrates SGLang with IBM Spyre in less than a week
A two-person team integrated SGLang with IBM Spyre in less than a week, using AI coding agents to build an open source plugin of roughly 1,500 lines. PyTorch says SGLang…

PyTorch serves Meta’s 816B Muse Spark Open on one TPU v7 host
PyTorch says it can serve Meta’s 816B-parameter Muse Spark Open mixture-of-experts model on a single TPU v7 host containing four chips. The system uses SGLang-TorchTPU…

Novita Sandbox Integrates With Miles for Agentic RL Training
Novita Sandbox is now a listed sandbox provider in Miles, RadixArk’s open-source framework for large-scale reinforcement learning and model post-training. The…

Modal releases Spindle, an open-source Tinker-compatible training server
Modal has released Spindle, an open-source training server that is compatible with the Tinker API from Thinking Machines and runs inside a customer's own Modal…

Google brings PyTorch-native vLLM and SGLang inference engines to TPU
Google has launched native PyTorch backends for vLLM and SGLang on TPU, built on a new runtime called TorchTPU. According to Google, the engines were developed with…

Modal shows stable RL training with mixed-precision, mixed-accelerator samplers
Modal says it has trained a large model with reinforcement learning (RL) using samplers on six kinds of accelerators and several numeric precisions, matching a…

NVIDIA Dynamo adds session IDs so inference servers can follow AI agents
NVIDIA Dynamo now ties an agent's many model calls together with a single session-level identifier, so the inference server can treat them as one program rather than…