ML Efficiency
Channel: #ml-efficiency
Co-leads:Â
Viraat - @viraat on Discord, @viraataryabumi on Twitter
Harsha - @majormelancholy on Discord, @Sree_Harsha_N on Twitter
Previous leads:
Bhavnick - @bhavnicksm on Discord, @BhavnickMinhas on Twitter
Recent Presentations
C4AI - ML Efficiency Group (2024-05-24 09:06 GMT-7)May 24, 2024
C4AI - ML Efficiency Group (2024-05-10 09:05 GMT-7)May 10, 2024
C4AI - ML Efficiency Group (2024-04-12 09:04 GMT-7)April 12, 2024
C4AI - ML Efficiency Group (2024-03-01 09:06 GMT-8)March 1, 2024
C4AI - ML Efficiency Group (2024-02-19 12:22 GMT-8)February 19, 2024
Alperen Gormez - Dataset Pruning Using Early Exit Networks (ML Eff.) (2023-11-18 09:05 GMT-8)Jen Iofinova - Accurate Neural Network Pruning Requires Rethinking Sparse Optimization (ML Theory & (2023-11-03 07:01 GMT-7)C4AI - ML Efficiency Group (2023-10-14 09:04 GMT-7)C4AI - ML Efficiency Group (2023-09-15 10:06 GMT-7)C4AI - ML Efficiency Group (2023-08-04 13:06 GMT-4)Join us to explore the theme of Transformer Inference Optimization.
After last session's paper on LLM.int8(), this week we will be going through "SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression" by Dettmers et. al.
The wonderful @Srishti Gureja will be presenting again!
C4AI - ML Efficiency Group (2023-07-21 13:04 GMT-4)C4AI - ML Efficiency Group (2023-05-12 13:04 GMT-4)C4AI - ML Efficiency Group (2023-04-28 13:12 GMT-4)On the Efficacy of Knowledge Distillation" by Hariharan et. al (2019)
Slides
C4AI - ML Efficiency Group (2023-04-14 13:03 GMT-4)Knowledge Distillation and the paper: Model Compression by Caruana et. al.
Materials from all past sessions