Summary of Seedlm: Compressing Llm Weights Into Seeds Of Pseudo-random Generators, by Rasoul Shafipour et al.
SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators
by Rasoul Shafipour, David Harrison, Maxwell Horton, Jeffrey Marker, Houman Bedayat, Sachin Mehta, Mohammad Rastegari, Mahyar Najibi, Saman Naderiparizi
First submitted to arxiv on: 14 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Large Language Models (LLMs) have revolutionized natural language processing, but their high runtime cost hinders widespread deployment. To address this challenge, our novel post-training compression method, SeedLM, uses seeds of pseudo-random generators to encode and compress model weights. Specifically, we find a seed for each block of weights, which is fed into a Linear Feedback Shift Register (LFSR) during inference to efficiently generate a random matrix. This matrix is then linearly combined with compressed coefficients to reconstruct the weight block. SeedLM reduces memory access and leverages idle compute cycles during inference, effectively speeding up memory-bound tasks by trading compute for fewer memory accesses. Our approach outperforms state-of-the-art compression methods that rely on calibration data, generalizing well across diverse tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large Language Models (LLMs) are super smart computers that can understand and generate human-like language, but they’re not very fast because they need to access lots of information in their “memory”. Our team found a way to make them faster by using a special trick called SeedLM. It’s like a secret code that helps the computer find the right answers quicker. We tested it on a really big and hard-to-compress model, and it worked amazingly well! Not only did it keep most of the original information, but it was also much faster than normal. |
Keywords
» Artificial intelligence » Inference » Natural language processing
