PinnedJldevtech·Apr 9, 2024Serverless Prompt Compression.Bing images: AI system landing on a planet of cash.
Jldevtech·Sep 2, 2025Making Flux Kontext go brrrSpeed Up Your Diffusion Models: 30% faster inference with torch.compile
Jldevtech·Feb 15, 2025From Bottleneck to Breakthrough: Achieving Compute-Bound PerformanceWhen working with large language models (LLMs), understanding accelerator memory requirements are crucial for optimizing performance and…
Jldevtech·May 28, 2024Small but Mighty: Fine-Tuning SLMs for Superior Evaluation Performance Over Larger ModelsBing (SLM vs LLM)
Jldevtech·Dec 14, 2022Setting up the Arduino RP2040 Connect to use with MicroPythonAfter my initial excitement and subsequent purchase following the release of the RP2040 Connect with support for micropython, that…
