6 papers
Quantizing Recursive Reasoning Models
Thorir Mar Ingolfsson, Wajeeha Tahir, Anna Tegon +3
Recursive reasoning models solve hard puzzles by applying compact, weight-tied blocks over many refinement steps. Because these blocks are reused many times, quantizing them create…
CHIMERA: A Flexible and Scalable 3.1 TOPS/W AI-MCU with Transformer Accelerator and 563 Gb/s Shared-L2 Memory Subsystem with QoS Guarantees
Lorenzo Leone, Philip Wiese, Gamze Ä°slamoÄlu +4
We present Chimera, a flexible and scalable Microcontroller Unit (MCU) designed to accelerate real-time inference of rapidly evolving transformer-based models at the ultra-low-powe…
FlatAttention: Dataflow and Fabric Collectives Co-Optimization for Efficient Multi-Head Attention on Tile-Based Many-PE Accelerators
Chi Zhang, Luca Colagrande, Renzo Andri +6
Multi-Head Attention (MHA) is a critical computational kernel in transformer-based AI models. Emerging scalable tile-based accelerator architectures integrate increasing numbers of…
MXDOTP: A RISC-V ISA Extension for Enabling Microscaling (MX) Floating-Point Dot Products
Gamze Ä°slamoÄlu, Luca Bertaccini, Arpan Suravi Prasad +3
Fast and energy-efficient low-bitwidth floating-point (FP) arithmetic is essential for Artificial Intelligence (AI) systems. Microscaling (MX) standardized formats have recently em…
VEXP: A Low-Cost RISC-V ISA Extension for Accelerated Softmax Computation in Transformers
Run Wang, Gamze Islamoglu, Andrea Belano +4
While Transformers are dominated by Floating-Point (FP) Matrix-Multiplications, their aggressive acceleration through dedicated hardware or many-core programmable systems has shift…
Toward Attention-based TinyML: A Heterogeneous Accelerated Architecture and Automated Deployment Flow
Philip Wiese, Gamze Ä°slamoÄlu, Moritz Scherer +5
One of the challenges for Tiny Machine Learning (tinyML) is keeping up with the evolution of Machine Learning models from Convolutional Neural Networks to Transformers. We address…