Products
Rebellions technology,
revolutionizing and redefining AI compute
Our small yet powerful chips have explosive potential.
From finance to hyperscale data centers, our chips will be the driving force
for the future defined by Artificial Intelligence.
Rebellions NPUs
REBEL
Shaping the Future of Gen AI
REBEL, featuring a scalable chiplet architecture, is a next-generation AI accelerator, specially engineered to enhance Large Language Models (LLMs) and Multi-Modal Models (MMMs). Built on Samsung’s advanced 4nm process, REBEL executes AI workloads with unparalleled energy efficiency. Capable of handling extensive workloads with remarkable speed, thanks to its high-bandwidth 144GB HBM3e memory and 800 Gigabit Ethernet network connectivity, REBEL is optimized for large-scale AI infrastructure deployment.
Stay Tuned for Our Big Reveal
ATOM™
Inference AI Accelerator for Data Centers
ATOM™ is a fast and power-efficient System-on-Chip for AI inference with remarkably low latency, conceived for deployment in data centers or cloud service providers.
With international recognition from the industry-standard benchmark MLperf™ v3.0, ATOM™ can be scaled to accelerate state-of-the-art AI models of various sizes.
With international recognition from the industry-standard benchmark MLperf™ v3.0, ATOM™ can be scaled to accelerate state-of-the-art AI models of various sizes.
ION™
Poised to Revolutionize the High-Frequency Trading Market
In the high-frequency trading (HFT) market, a microsecond can make a huge difference. ION™ was specifically tailored for this finance industry. Within just one year of inception, Rebellions introduced this powerful chip to the market, marking a significant milestone in our pursuit of technological excellence.
Roadmap
Explosive expansion on compute and external memory
64x DNCs
REBEL-Quad
REBEL-Quad
(4x chiplet)
- 175B+ LLM acceleration
- Samsung 4nm EUV
- HBM3E 144GB (4.8TB/sec)
16x DNCs
REBEL-Single
CXL-PIM
- CXL-based PNM/PIM
REBEL-Single
(1x chiplet)
- sLLM acceleration
- Samsung 4nm EUV
- HBM3E 36GB (1.2TB/sec)
8x DNCs
ATOM™ Plus
ATOM™
ATOM™ Plus
(high perf)
ATOM™
(low power)
- BERT, Vision Transformers, 7B+ generative AI
- Samsung 5nm EUV (Mass in 4Q 2023)
- PCle gen5 64GB/s, GDDR6 256GB/s
ION™
2021~2023
2024
2025
2026
* DNC (Dual Neural Core) : Our fundamental design granule for multiple product lines. This proprietary IP is continually maintained, updated and patented by Rebellions' DNC team.
Up next
