Stealth 7-year startup Kepler debuts AI memory beyond HBM, secures up to $245M in US government support
npinto · x · 2026-09-10
Kepler, founded by veteran chip engineers and stealthy for 7 years, just unveiled its plan for "AI's new memory": inference-optimized memory targeting SRAM-level bandwidth-per-watt with capacity beyond SRAM and HBM, via 3D stacking and novel materials — claiming leading-edge chips are possible without EUV.
Key facts:
- Selected for up to $245M in proposed U.S. Department of Commerce support
- Sampling by end of 2026, production ramping in 2027, planning 2028–30 capacity
- Team credits include 3D logic stacking, seven generations of DRAM, first-to-market 232-layer NAND
- Thesis: orders of magnitude more chips per dollar and datacenter energy pushed to physical limits
Related event: Stealthy chip startup Kepler emerges with new AI memory beyond silicon(8 posts)→
More from Infra
- DeepSpeed shows AutoEP/AutoTP/AutoSP parallelism gains, hosts office hours — PyTorch · 2026-10-27
- Cloudflare Durable Objects validated as top architecture for AI agent WebSocket servers — tristanbob · 2026-10-27
- Gary Marcus: With Q3 data added, Anthropic's compute-efficiency growth shows deceleration — GaryMarcus · 2026-10-27
- SpaceX locks in $40B GPU financing deal with Apollo, the largest ever committed — TechCrunch AI · 2026-10-27
- Inference is just Kubernetes with a multi-trillion-dollar market, and the communities overlap — matt_slotnick · 2026-10-27
- vLLM eyes Rust migration as inference engines race to rewrite the stack — AccBalanced · 2026-10-27