NVIDIA AI Developer

If you’re seeing this, you should be following @NVIDIAAI. Our developer team has moved next door to @NVIDIAAI. Join us there to stay up to date on the latest products, models, deep dives, and more. Thanks to everyone who’s been with us here. We hope to see soon 💚

We developed a simple, sample-efficient online RL technique for post-training image generation models. We see it as a possible steerable alternative to CFG, driven by any scalar reward, including human preference.

I trained a 12M parameter LLM on my own ML framework using a Rust backend and CUDA kernels for flash attention, AdamW, and more. Wrote the full transformer architecture, and BPE tokenizer from scratch. The framework features: - Custom CUDA kernels (Flash Attention, fused LayerNorm, fused GELU) for 3x increased throughput - Automatic WebGPU fallback for non-NVIDIA devices - TypeScript API with Rust compute backend - One npm install to get started, prebuilt binaries for every platform Try out the model for yourself: mni-ml.github.io/demos/trans… Built with @_reesechong. Check out the repos and blog if you want to learn more. Shoutout to @modal for the compute credits allowing me to train on 2 A100 GPUs without going broke cc @sundeep @GavinSherry