Tooling7d ago
Google and Meta open-source TorchTPU: native PyTorch on TPUs, where porting is as simple as .to("cuda") to .to("tpu"), with native TPU backends for vLLM and SGLang
At PyTorch Conference 2026 on Oct 20, Google open-sourced TorchTPU on GitHub, co-developed with Meta's PyTorch team, making TPUs a native PyTorch device alongside GPUs and CPUs: eager mode and torch.compile, about 450 ATen ops, and torch.distributed collectives. Google also released vLLM-TorchTPU and SGLang-TorchTPU engines, integrations with TorchTitan, Ray, VeRL and Hugging Face Transformers v5 (device_map="tpu"), and a preview TPU agent suite for coding assistants such as Claude Code and Antigravity. AWS shipped the comparable TorchNeuron a day earlier.
Infrastructure10d ago
SemiAnalysis Breaks Down 1.3B Tokens/$ AgentX Record: vLLM + Inferact Disaggregated Serving Beats Aggregated B300 by 4x, While Cline Highlights Multi-Harness RL
SemiAnalysis published the architectural breakdown behind the 1.3B tokens per dollar TCO record on AgentX: vLLM and Inferact utilized Prefill/Decode disaggregated serving at hyperscaler volume pricing to achieve 4x better cost-efficiency than an aggregated NVIDIA B300 configuration. Concurrently, open-source coding agent Cline reported that DeepSeek-V4.1-Flash-1017 beats GPT-5.6-Sol on Terminal-Bench at ~17x lower cost (+35% over prior V4.1-Flash) purely by scaling RL training across multiple coding agent harnesses.
Hardware9d ago
SemiAnalysis Discloses Google & Inferact TPUv7 Submission: TorchTPU vLLM Megakernels Drive 2.8T Kimi K3, Surpassing GB200 NVL72 and B300 in High-Interactivity TCO
SemiAnalysis revealed the first Google TPUv7 benchmark submission for the 2.8T Kimi K3 MoE model, led end-to-end by Inferact (the creators of vLLM) and Google using the TorchTPU vLLM stack. At a hardware rental cost of just $1.21/chip-hour (vs $2.31 for GB300 and $1.86 for GB200), TPUv7 delivers ~2.2M tokens per $1 TCO in the ultra-high interactivity regime (~390 tok/s/user), outpacing NVIDIA GB200 NVL72, B300, and AMD MI355X on cost-performance.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.