#model_quantization — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #model_quantization, aggregated by home.social.
-
Gemlite: Towards Building Custom Low-Bit Fused CUDA Kernels
https://mobiusml.github.io/gemlite_blogpost/
#ycombinator #Model_Quantization #CUDA #Machine_Learning #Model_Compression #Transformer_Models #Neural_Networks #AI_Optimization