TensorFlow

Accelerating AI on Edge — Chintan Parikh and Weiyi Wang, Google DeepMind

May 5, 2026 · 23:58

Chintan Parikh and Weiyi Wang from Google DeepMind present Gemma 4E edge models (2B and 4B) and the LiteRT framework for on-device AI, arguing that edge AI delivers latency, privacy, offline capability, and cost savings. The Gemma 4E models introduce agentic capabilities including built-in function calling, structured JSON output, and chain-of-thought reasoning, all optimized for hardware-native support across CPUs, GPUs, and NPUs. LiteRT supports cross-platform deployment on Android, iOS, macOS, Linux, Windows, and IoT devices like Raspberry Pi, with a CLI tool and AI Edge portal for benchmarking. Performance benchmarks show up to 56 tokens per second on iOS, 30x speedups with NPU acceleration, and 35x faster than Llama on mobile. The Gallery app demonstrates on-device skills such as Wikipedia querying, mood tracking, photo-to-music generation, and voice agents, with open-source code and a Hugging Face repository. Q&A addresses use cases like local security camera face recognition, LiteRT vs TensorRT on Orin, multi-agent architectures, and audio model support.

Information Retrieval from the Ground Up - Philipp Krenn, Elastic

Jul 27, 2025 · 1:48:07

Philipp Krenn of Elastic demonstrates that vector search is only a feature of information retrieval, not its foundation, in this hands-on workshop on retrieval for RAG. He contrasts classic keyword search—using tokenization, stemming, stopword removal, and BM25 scoring with the inverted index—with sparse (Elser/Splade) and dense (OpenAI text-embedding-small) vector embeddings. Krenn explains why hybrid search, combining lexical and semantic methods via reciprocal rank fusion (RRF), outperforms any single approach, especially for brand or exact-match queries where keyword search remains superior. He also covers scoring normalization, chunking strategies, and the new `text_similarity_reranker` retriever, showing how Elasticsearch's retrievers API enables two-stage retrieval with a cross-encoder for re-ranking. The session emphasizes that retrieval quality depends on evaluating against a golden dataset or LLM-as-judge, and that 'it depends' is the correct answer for choosing between PgVector and dedicated search engines.

Luminal - Search-Based Deep Learning Compilers - Joe Fioti

Jun 3, 2025 · 24:35

Joe Fioti presents Luminal, a search-based deep learning compiler that simplifies ML libraries to 12 primitive operations and uses search to automatically discover optimized kernels like flash attention. By representing models as directed acyclic graphs of these simple ops, Luminal keeps its codebase under 5,000 lines yet can run all major models. Its compiler applies 20-25 rewrite rules to search through equivalent GPU kernels, profiling to find the fastest—automatically rediscovering flash attention, an algorithm that took five years for the industry to develop. Data movement accounts for 99% of runtime, so kernel fusion merges many ops into one, dramatically speeding execution. An external auto-grad crate adds training support without altering the core. Future plans include supporting AMD, TPUs, and a serverless cloud that exports optimized graphs for inference.

Unveiling the latest Gemma model advancements: Kathleen Kenealy

Feb 9, 2025 · 16:25

Kathleen Kenealy, technical lead of the Gemma team at Google DeepMind, unveils the latest advances in the Gemma model family, including the launch of Gemma 2 in 9B and 27B parameter sizes, which outperform models two to three times larger, such as LLaMA 3 70B. She also introduces PALI Gemma, a multimodal model combining Siglip Vision Encoder with Gemma 1.0 for image-text tasks. The episode highlights Gemma's responsible-by-design approach, broad framework support (TensorFlow, Jax, PyTorch, etc.), and the release of the Gemma cookbook with 20 recipes. Kenealy emphasizes that Gemma 2 is optimized for easy integration and fine-tuning, available on Google AI Studio, and invites the community to build and share their projects.

Building security around ML: Dr. Andrew Davis

Feb 8, 2025 · 25:01

Dr. Andrew Davis, Chief Data Scientist at HiddenLayer, argues that machine learning models remain highly vulnerable to adversarial attacks despite a decade of research, and defenses must be layered with observability, logging, and skeptical data handling. He details how ImageNet's URL-based distribution enables data poisoning via expired domains, and how model theft can replicate a LLaMA 7B model's performance for just $600 in OpenAI queries. Adversarial examples still evade robust defenses, with best-case robustness only 50-60% against advanced attacks, and multimodal LLMs amplify the threat as pixel-level modifications are far harder to detect than text prompt injections. Spotlighting — encoding data in base64 to prevent instruction-following — is a promising prompt injection defense, but attackers can craft readable base64 strings to bypass it. The ML supply chain on Hugging Face is fraught with risk: models can execute arbitrary code via Lambda layers or TensorFlow functions, so verifying provenance, scanning for malware, and sandboxing are critical. Finally, software vulnerabilities in tools like Ollama (with recent RCE CVEs) demand the same patching discipline as traditional…

Unlocking Developer Productivity across CPU and GPU with MAX: Chris Lattner

Jul 25, 2024 · 18:33

Chris Lattner, CEO of Modular, presents MAX, a unified AI framework that accelerates Gen AI inference by combining CPU and GPU programming into a single Pythonic model, and Mojo, a new programming language that extends Python to systems programming with 100–1000x speedups. Lattner argues that current fragmentation across PyTorch, ONNX, TensorRT, and hardware-specific libraries slows innovation, and MAX replaces the entire stack—including cuDNN and Intel MKL—with a consistent, compiler-driven approach. He demonstrates that MAX's Int4/Int6 quantization achieves 5x faster performance than llama.cpp on cloud CPUs, and that its GPU matrix multiplication beats NVIDIA's cuBLAS by up to 30%. Mojo enables developers to write for loops and tokenizers (e.g., for LLaMA 3) in Python-like syntax without dropping to C++ or Rust. MAX is free and available now for CPU inference; GPU support launches in September with early access via Discord.