Scaling Agentic Inference Across Heterogeneous Compute with Zain Asgar - #757
About this episode
Zain Asgar discusses heterogeneous AI inference and the challenges of running AI workloads across diverse hardware.
In this episode, Zain Asgar, co-founder and CEO of Gimlet Labs, joins us to discuss the heterogeneous AI inference across diverse hardware. Zain argues that the current industry standard of running all AI workloads on high-end GPUs is unsustainable for agents, which consume significantly more tokens than traditional LLM applications. We explore Gimlet’s approach to heterogeneous inference, which involves disaggregating workloads across a mix of hardware—from H100s to older GPUs and CPUs—to optimize unit economics without sacrificing performance. We dive into their "three-layer cake" architecture: workload disaggregation, a compilation layer that maps models to specific hardware targets, and a novel system that uses LLMs to autonomously rewrite and optimize compute kernels. Finally, we discuss the complexities of networking in heterogeneous environments, the trade-offs between numerical precision and application accuracy, and the future of hardware-aware scheduling. The complete show notes for this episode can be found at https://twimlai.com/go/757.
People in this episode
Host: Sam Charrington
Guest: Zain Asgar
Topics covered
- AI inference
- heterogeneous compute
- hardware optimization
- LLMs
- networking complexities
Keywords
- AI workloads
- GPUs
- CPUs
- workload disaggregation
- compute kernels
Mentioned in this episode
Organizations: Gimlet Labs
More episodes of The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
- How Capital One Delivers Multi-Agent Systems with Rashmi Shetty - #765
- The Race to Production-Grade Diffusion LLMs with Stefano Ermon - #764
- Agent Swarms and Knowledge Graphs for Autonomous Software Development with Siddhant Pardeshi - #763
- AI Trends 2026: OpenClaw Agents, Reasoning LLMs, and More with Sebastian Raschka - #762
- The Evolution of Reasoning in Small Language Models with Yejin Choi - #761
- Intelligent Robots in 2026: Are We There Yet? with Nikita Rudin - #760
Explore listener stats, chart rankings, contacts and more on the The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) podcast page.