Goblin
News
AI news by
promptgoblins.ai
|
News
About
News
About
Filtered by:
Model Compression
Clear
Titles
Summaries
6
Quantization-Aware Healing Makes 4-Bit Compressed Models Outperform Full-Precision Originals
Research
1
Aug 25
6
Quantization-Aware Healing Makes 4-Bit Compressed Models Outperform Full-Precision Originals
Research
· 1 src · Aug 25
Discuss
6
ToMoE: Technique Converts Dense LLMs to Mixture-of-Experts via Dynamic Pruning Without Permanent Parameter Loss
Research
1
Aug 24
6
ToMoE: Technique Converts Dense LLMs to Mixture-of-Experts via Dynamic Pruning Without Permanent Parameter Loss
Research
· 1 src · Aug 24
Discuss
6
New Paper Cuts LLM Knowledge Distillation VRAM in Half via Offline Caching and Chunked KL Loss
Research
1
Aug 10
6
New Paper Cuts LLM Knowledge Distillation VRAM in Half via Offline Caching and Chunked KL Loss
Research
· 1 src · Aug 10
Discuss
8
Multiverse Computing Raises $570M Series C at $1.7B Valuation for Quantum-Physics-Based LLM Compression
Markets
1
Jul 27
8
Multiverse Computing Raises $570M Series C at $1.7B Valuation for Quantum-Physics-Based LLM Compression
Top
Markets
· 1 src · Jul 27
Discuss
Filters
Signal
Title
Category
Sources
Posted
Discuss
