Tensordyne publishes inference whitepaper: TSMC 3nm chip taped out with Broadcom
kimmonismus · x · 2026-09-04
Inference-chip startup Tensordyne published its whitepaper claiming the highest fast-token throughput per megawatt in the industry. Key points: bit-accurate log math is locked in, the chip has taped out with Broadcom and is in wafer fab on TSMC 3nm, and compute-tray system bring-up with the HPE Juniper scale-up fabric is ahead of schedule.
More from Infra
- DeepSeek's token density yields ~$38/GPU-hr revenue vs $3.50 for raw IaaS, engineer estimates — bookwormengr · 2026-10-21
- Sizing a 1 GW datacenter: ~522,000 Blackwell GPUs fit inside — bookwormengr · 2026-10-21
- At 85% billable uptime, a 1 GW fleet supplies 3.89B GPU-hours/year — bookwormengr · 2026-10-21
- DeepSeek's production density reportedly hits ~$38 per GPU-hour at saturation — bookwormengr · 2026-10-21
- PyTorch details KTIR and Dataflow Scheduler behind IBM's Spyre accelerator backend — PyTorch · 2026-10-21
- Indie dev replaces $1k OpenAI bill with a YAML pipeline on spot GPUs and vLLM — cmm324 · 2026-10-21