HBM3e Advanced-packaging chiplet for all workloads
GenAI for All, Maximum Impact at Minimal Cost
Designed to power large-scale AI systems, REBEL achieves the highest level of energy efficiency while delivering top performance. Equipped with the latest HBM3E, REBEL demonstrates outstanding computing speed and throughput per Watt, making state-of-the-art AI services more accessible. REBEL gives companies the extra edge to stay ahead of the competition.
GenAI for All, Maximum Impact at Minimal Cost
Designed to power large-scale AI systems, REBEL achieves the highest level of energy efficiency while delivering top performance. Equipped with the latest HBM3E, REBEL demonstrates outstanding computing speed and throughput per Watt, making state-of-the-art AI services more accessible. REBEL gives companies the extra edge to stay ahead of the competition.
Performance at Any Scale: from a Single Card to a GenAI Datacenter
Combine four dies onto a single IC chip, connected through the state-of-the- art advanced chiplet packaging. Scale beyond a single card to multi-rack configurations, able to support any multi-modal models for years to come. Achieve greater sustainability of accelerating AI workloads for the upcoming power-hungry GenAI datacenters.
Additional data available! Features, portability, process node, and more can be viewed by logging in with your Chiplet Marketplace account.
- See the entire HBM3e Advanced-packaging chiplet for all workloads datasheet
- Get in contact with HBM3e Advanced-packaging chiplet for all workloads Supplier
Video
REBEL: Shaping the Future of Gen AI
Get ready for REBEL, a next-generation AI accelerator shaping the future of Gen AI. Featuring a scalable chiplet architecture and high-bandwidth 144GB HBM3e memory, REBEL takes Large Language Models (LLMs) and Multi-Modal Models (MMMs) to new heights. Coming Q4 2024.
Related Chiplets
- 400G Transmitter Chiplet for 400G, 800G and 1.6T Pluggable Transceivers
- Arm Compute Chiplet
- High-Density Electronic-Photonic Chiplet
- Machine learning accelerator chiplet implemented in 12nm
- Heterogeneous FPGA chiplet implemented in 12nm
- Quad-core 64-bit RISC-V ISA, dual-issue, in-order application class processor chiplet implemented in 12nm