y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#submodule-pruning News & Analysis

1 article tagged with #submodule-pruning. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

1 articles
AIBullisharXiv – CS AI · 7h ago7/10
🧠

From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression

Researchers introduce SubFit, a post-training compression method for Large Language Models that operates at the submodule level rather than full-layer granularity, achieving superior perplexity-accuracy trade-offs. The approach selects non-contiguous Attention and FeedForward submodules with individual fitted residual bypasses, delivering 84.6% downstream accuracy retention at 25% sparsity compared to 81.6% for existing methods.

🏢 Perplexity