AgentDish directory

hardware acceleration

Accepted listings with this tag.

Listing	Category	Score	Trend	Checked
#875 ↓ -6 Taalas-Style On-Chip Weights on a $250 FPGA A live demo and write-up showing a 3.16M-parameter INT4 transformer running entirely in on-chip memory on a Xilinx Kria KV260 FPGA, with measured token rates and hardware details.	AI Hardware / On-device LLM demo	84	↓ -6	32 days ago	Details
#1826 → 0 Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding arXiv paper on a self-speculative decoding framework for speeding up reasoning LLM inference on edge hardware, with hardware co-design and reported speedups.	Research / AI/ML Paper	77	→ 0	105 days ago	Details