07/22 07:05 AM dev.to Running Qwen3 Through the ExecuTorch MLX Delegate: Up to 4.52x Faster on M1 Max #PYTHON #POLITICS #APPLESILICON #LLM #PYTORCH
07/21 07:05 AM dev.to Testing PyTorch 2.13 MPS FlexAttention on M1 Max: Up to 7.83x Faster for Sparse Attention #PYTORCH #PYTHON #MACHINELEARNING #POLITICS #APPLESILICON
06/17 06:40 PM dev.to Twenty years of Linux, and now I run my own AI #OPENSOURCE #LOCALAI #APPLESILICON #POLITICS #EARTHQUAKE
05/31 05:46 PM dev.to M4 Pro vs M5 Pro: Which Apple Silicon Chip Wins? #POLITICS #M5PRO #MACBOOKPRO #M4PRO #APPLESILICON
