Gleam Lab · Tag Archive
Tag: PTQ
2 articles collected by topic for tutorials, cases, engineering practice, and research notes.
AI Research 42 - Multimodal Large Model Quantization: From FP32 to INT4, the Final Summary
Survey outline for multimodal large model quantization schemes: from FP32 to INT4. Core goal is model capability retention, compression efficiency 50-75%...
AI Research 36 - Comprehensive Analysis of Multimodal Large Model Quantization
This comprehensive overview systematically introduces mainstream quantization techniques in multimodal models.