#Model Architecture

3 articles with this tag

CPU LLMs: Architecture First, Size Later
AI Research

CPU LLMs: Architecture First, Size Later

New research rethinks SLM design, prioritizing CPU efficiency from scratch for superior performance and speed.

2 months ago
Matryoshka: Nested LMs for Efficiency
AI Research

Matryoshka: Nested LMs for Efficiency

The Matryoshka training framework nests language model sub-models, drastically cutting compute costs and enhancing speculative decoding throughput while maintaining performance parity.

2 months ago
Heterogeneous LLMs Unite for Performance
AI Research

Heterogeneous LLMs Unite for Performance

Novel multi-model LLM architecture composes heterogeneous frozen models, achieving superior performance with minimal trainable parameters and exhibiting emergent routing.

7 months ago