One of the authors here. We're diving deep into the workings of ai inference optimization. This deep-dive post reports on our actual runs with various agentic coding setups using quantization.
Some caveats here, which I'll get back to, but useful for anyone considering to use quantization.
One of the authors here. We're diving deep into the workings of ai inference optimization. This deep-dive post reports on our actual runs with various agentic coding setups using quantization.
Some caveats here, which I'll get back to, but useful for anyone considering to use quantization.