general_compute partners with Cerebras to deploy 'world's fastest inference'
eptwts · x · 2026-09-30
generalcompute announced a partnership with Cerebras to deploy what it calls the world's fastest inference, claiming 20x faster AI while noting that usable compute is scarce.
The setup uses GPUs for prefill combined with Cerebras for decoding, keeping costs down. First tokens are expected live in Q1 2027.
Related event: General Compute Partners with Cerebras to Launch World's Fastest Inference(2 posts)→
More from Infra
- Mobile AI Factory: agents auto-build on-device SLMs with 19x less GPU time — pmttyji · 2026-11-16
- Stratechery's Fictional Obituary: Imagining Jensen Huang's 2026 Exit From Nvidia — Gregory_C_Allen · 2026-11-16
- vLLM serves DeepSeek V4.1-Flash at 954K tokens/s per GPU, $38.96/GPU-hour on GB300 NVL72 — bookwormengr · 2026-11-16
- Colossus 2's 1.2M B200s could generate ~$400B/year in tokens at DeepSeek Flash rates — bookwormengr · 2026-11-16
- BIS issues rule blocking remote access to US AI chips via third-country data centers — teortaxesTex · 2026-11-16
- Qdrant 1.20.1: 50% fewer cold-storage reads, ~2x faster quantization, agent-ready setup — qdrant_engine · 2026-11-16