Deep Dives

is a to Optimizing Data Transfer in AI/ML Workloads where we demonstrated using NVIDIA Nsight™ Systems (nsys) in studying and solving the common data-loading bottleneck — occurrences where the GPU idles while it waits for input...

Optimizing Multimodal Agents Multimodal AI agents, those who can process text and pictures (or other media), are rapidly entering real-world domains like autonomous driving, healthcare, and robotics. In these settings, we now have traditionally used...

is an annual advent calendar of programming puzzles which might be themed around helping Santa’s elves prepare for Christmas. The whimsical setting masks the proven fact that many puzzles call for serious algorithmic...

an LLM can see before it generates a solution. This includes the prompt itself, instructions, examples, retrieved documents, tool outputs, and even the prior conversation history. Context has a huge effect on answer quality....

a contemporary vector database—Neo4j, Milvus, Weaviate, Qdrant, Pinecone—there may be a really high likelihood that Hierarchical Navigable Small World (HNSW) is already powering your retrieval layer. It is kind of likely you probably did...

a decade working in analytics, I firmly imagine that observability and evaluation are essential for any LLM application running in production. Monitoring and metrics aren’t just nice-to-haves. They ensure your product is functioning...

That is the primary in a two-part series on distributed computing using Ray. This part shows the way to use Ray in your local PC, and part 2 shows the way to scale Ray...

a , a deep learning model is executed on a dedicated GPU accelerator using input data batches it receives from a CPU host. Ideally, the GPU — the dearer resource — needs to...