Speculative Decoding and Efficient LLM Inference with Chris Lott - #717

Speculative Decoding and Efficient LLM Inference with Chris Lott - #717

Author: Sam Charrington February 4, 2025 Duration: 1:16:30
Today, we're joined by Chris Lott, senior director of engineering at Qualcomm AI Research to discuss accelerating large language model inference. We explore the challenges presented by the LLM encoding and decoding (aka generation) and how these interact with various hardware constraints such as FLOPS, memory footprint and memory bandwidth to limit key inference metrics such as time-to-first-token, tokens per second, and tokens per joule. We then dig into a variety of techniques that can be used to accelerate inference such as KV compression, quantization, pruning, speculative decoding, and leveraging small language models (SLMs). We also discuss future directions for enabling on-device agentic experiences such as parallel generation and software tools like Qualcomm AI Orchestrator. The complete show notes for this episode can be found at https://twimlai.com/go/717.

Hosted by industry analyst and commentator Sam Charrington, The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) serves as a vital conduit between cutting-edge research and its real-world implications. This isn't just a series of technical lectures; it's a series of conversations that unpack how AI and machine learning are actively reshaping industries and societal structures. Each episode connects you directly with leading researchers, engineers, and innovative thinkers who are defining the frontiers of the field. The discussions go beyond abstract theory to explore the practical challenges, ethical considerations, and business transformations driven by these technologies. Whether you're a data scientist deep in the code, a tech-savvy leader strategizing implementation, or simply fascinated by the future of intelligent systems, this podcast provides the context and depth needed to stay informed. By focusing on the people behind the algorithms and the ideas powering the platforms, Sam creates a resource that is both intellectually substantive and genuinely engaging, building a thoughtful community around one of the most significant technological shifts of our time.
Author: Language: English Episodes: 100

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Podcast Episodes
AI Agents: Substance or Snake Oil with Arvind Narayanan - #704 [not-audio_url] [/not-audio_url]

Duration: 54:22
Today, we're joined by Arvind Narayanan, professor of Computer Science at Princeton University to discuss his recent works, AI Agents That Matter and AI Snake Oil. In “AI Agents That Matter”, we explore the range of agen…
AI Agents for Data Analysis with Shreya Shankar - #703 [not-audio_url] [/not-audio_url]

Duration: 48:24
Today, we're joined by Shreya Shankar, a PhD student at UC Berkeley to discuss DocETL, a declarative system for building and optimizing LLM-powered data processing pipelines for large-scale and complex document analysis…
Automated Design of Agentic Systems with Shengran Hu - #700 [not-audio_url] [/not-audio_url]

Duration: 59:30
Today, we're joined by Shengran Hu, a PhD student at the University of British Columbia, to discuss Automated Design of Agentic Systems (ADAS), an approach focused on automatically creating agentic system designs. We exp…
The Building Blocks of Agentic Systems with Harrison Chase - #698 [not-audio_url] [/not-audio_url]

Duration: 59:17
Today, we're joined by Harrison Chase, co-founder and CEO of LangChain to discuss LLM frameworks, agentic systems, RAG, evaluation, and more. We dig into the elements of a modern LLM framework, including the most product…
Genie: Generative Interactive Environments with Ashley Edwards - #696 [not-audio_url] [/not-audio_url]

Duration: 46:51
Today, we're joined by Ashley Edwards, a member of technical staff at Runway, to discuss Genie: Generative Interactive Environments, a system for creating ‘playable’ video environments for training deep reinforcement lea…
Bridging the Sim2real Gap in Robotics with Marius Memmel - #695 [not-audio_url] [/not-audio_url]

Duration: 57:21
Today, we're joined by Marius Memmel, a PhD student at the University of Washington, to discuss his research on sim-to-real transfer approaches for developing autonomous robotic agents in unstructured environments. Our c…