EdgeCIM: A Hardware-Software Co-Design for CIM-Based Acceleration of Small Language Models
cs.AR, cs.AI
Submitted: 2026-04-13
Updated: 2026-10-27
Code: https://github.com/ggerganov/llama.cpp
Terminology
Sources
- LLaMA: Open and Efficient Foundation Language Models
- BF-IMNA: A Bit Fluid In-Memory Neural Architecture for Neural Network Acceleration
- Small Language Models: Survey, Measurements, and Insights
- Mixture Content Selection for Diverse Sequence Generation
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- Full Stack Optimization of Transformer Inference: a Survey
- TinyLlama: An Open-Source Small Language Model
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Qwen2.5 Technical Report
- SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
- Qwen3 Technical Report
Related papers
- Embedded Arena: Iterative Optimization via Hardware Feedback
- WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization
- SparsePixels: Efficient Convolution for Sparse Data on FPGAs
- Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats
- AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving
- RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design