논문 리뷰

1.YOLOv5 아키텍쳐 분석

post-thumbnail

2.[paper review] Accelerating Transformer Inference for Translation via Parallel Decoding

post-thumbnail

3.self attention 이해하기

post-thumbnail

4.[paper review] Improving Language Understanding by Generative Pre-Training

post-thumbnail

5.[paper review] Unlocking Efficiency in Large Language Model Inference : A Comprehensive Survey of Speculative Decoding

post-thumbnail

6.[paper review] GPTQ: ACCURATE POST-TRAINING QUANTIZATION FOR GENERATIVE PRE-TRAINED TRANSFORMERS

post-thumbnail

7.[paper review] MEDUSA: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

post-thumbnail

8.[paper review] GLIDE with a CAPE

post-thumbnail

9.[paper review] Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

post-thumbnail

10.Eagle

post-thumbnail