SGLang

The Future of AI Infra: from Kubernetes to Agent Sandboxes — Akshat Bubna, Modal CTO

Jul 8, 2026 · 59:10

Modal CTO Akshat Bubna explains how the cloud platform evolved from a serverless runtime to an AI cloud built for elastic inference, agent sandboxes, and post-training workloads. He argues that Kubernetes was never designed for bursty GPU-heavy AI workloads, so Modal built a decorator-based infrastructure that co-locates compute requirements with code. The company added GPUs a year before ChatGPT and now powers inference for custom models at Suno, Runway, and robotics firms, using GPU snapshotting to slash cold starts. Modal's new Auto Endpoints incorporate open-source DeFlash speculative decoding for frontier-level performance. For reinforcement learning rollouts, Modal provides up to 100,000 sandboxes simultaneously. The platform spans 17 cloud providers, features private IPv6 networking via eBPF, and supports serverless multi-node training with RDMA. Bubna also reveals Modal's shift from developer experience to agent experience, noting that agents benefit from the same minimalist SDK and observability tools that humans use.

Agent Inference at the "Speed of Light" — How NVIDIA moves like a $4.3 Trillion Startup

Mar 8, 2026 · 1:26:00

NVIDIA's Nader Khalil and Kyle Kranen join Swyx and Vibhu to explain how the company moves like a $4.3 trillion startup through speed-of-light (SOL) first-principles thinking, agent security boundaries, and the Dynamo inference engine. They argue agents should only do two of three things (files, internet, code) to prevent vulnerabilities, and detail Brev's acquisition to improve developer UX with one-click GPU access and DGX Spark integration. Kyle describes Dynamo as a data center scale inference engine that optimizes serving by scaling out, using prefill/decode disaggregation, Kubernetes-based scheduling, and model-hardware co-design to improve cost, latency, and quality. The episode covers SOL's role in creating urgency, long-context limits and potential 'unhobblers' like multi-head latent attention, and the shift toward CLI-first agent workflows for enterprise tools.

Goodfire AI’s Bet: Interpretability as the Next Frontier of Model Design — Myra Deng & Mark Bissell

Feb 5, 2026 · 1:08:41

Goodfire AI's Mark Bissell and Myra Deng argue that interpretability is the next frontier for model design, using their recent $150M Series B at $1.25B valuation to scale surgical edits of model internals beyond post-hoc poking. They explain how their platform detects behaviors like sycophancy and reward hacking, enabling targeted unlearning without wrecking capabilities. The episode covers real-world deployments from Rakuten's PII guardrails to life science partnerships with Mayo Clinic finding Alzheimer's biomarkers. Mark demonstrates real-time steering of a trillion-parameter Kimi K2 model, while Myra details how SAEs sometimes underperform probes for detection tasks. They envision a future where interpretability guides training so customization isn't brute-force guesswork.

[State of Research Funding] Beyond NSF, Slingshots, Open Frontiers — Andy Konwinski, Laude Institute

Dec 31, 2025 · 22:34

Andy Konwinski, co-founder of Databricks and Perplexity, launches Laude Institute—a dual venture fund and nonprofit to accelerate the path from open research to breakout companies. At NeurIPS, he explains how Laude's Slingshot program funds projects like DSPy, Terminal Bench, and LMArena, and why the NSF's $1B/year for CS is insufficient, needing $10-100B for frontier AI. He argues Chinese labs (Moonshot, DeepSeek) now outpublish US because OpenAI and others stopped sharing; Open Frontiers, a live-streamed conference in SF, aims to unite top open researchers (Yann LeCun, François Chollet, Jan Leike) to reclaim global leadership. The episode also spotlights the emerging 'post-post-training' layer—prompt optimization, context management, RAG—and why research teams with multiple co-founders (like Databricks' eight) are the new gold standard for AI startups.

⚡️Mercury: Ultra-Fast Diffusion LLMs — Estefano Ermon, CEO Inception Labs

Aug 4, 2025 · 28:07

Stefano Ermon of Inception Labs explains why diffusion language models like their Mercury Coder can match GPT-4.1 Nano and Claude Haiku in intelligence while delivering 5–10× faster inference at 737–1109 tokens/sec on H100s, built on score-based generative model foundations he pioneered at Stanford. He details the coarse-to-fine generation process that modifies multiple tokens per network evaluation, the required end-to-end training from scratch (no fine-tuning existing LLMs), and how post-training pipelines use specialized DPO for preference alignment. Ermon identifies latency-sensitive applications—voice agents, IDEs, vibe coding—as the killer use case, acknowledges they aren't yet frontier-level but sees a future where diffusion dominates due to efficiency gains, and notes the challenge of open-sourcing given proprietary inference engines and kernels.

The Shape of Compute (Chris Lattner of Modular)

Jun 13, 2025 · 1:18:18

Chris Lattner of Modular explains how his company is breaking the CUDA monopoly with Mojo and MAX, matching NVIDIA's best inference performance on AMD and NVIDIA GPUs. After three years in R&D, Modular open-sourced its stack and now delivers state-of-the-art Llama 3 serving at over 800 tokens per second. Mojo, a Python-family language, runs kernels faster than Rust and can extend Python without bindings, while MAX provides a full inference framework with automatic kernel fusion and cluster management. Unlike VLLM or SGLang, Modular's container is just a gigabyte, fully open source, and not reliant on proprietary CUDA blobs. DeepSeek's low-level PTX work validated the approach, but Lattner emphasizes that Mojo's portability avoids rewriting kernels for each new GPU architecture. He also details his daily routine, using Cursor for coding, and hiring "elite nerds" to grow the team.

DeepSeek V3, SGLang, and the state of Open Model Inference in 2025 (Quantization, MoEs, Pricing)

Jan 19, 2025 · 57:18

Amir Haghighat and Yineng Zhang from Baseten explain how they serve DeepSeek V3, a 671-billion-parameter MoE model requiring H200 clusters with FP8 support, making it the top open-weights model. They detail Baseten’s dedicated inference model (no shared endpoints) and its reliance on SGLang for performance gains like Radix prefix caching and MLA attention support. Yineng highlights SGLang’s edge over vLLM and TensorRT-LLM in usability and customization, especially for large models. Amir outlines three pillars for mission-critical inference: model-level performance (via frameworks like SGLang), horizontal scaling across regions and clouds, and low-latency multi-model workflows. The episode also covers quantization trends, MoE architecture, and speculative decoding as key enablers for open model deployment.

In the Arena: How LMSys changed LLM Benchmarking Forever

Nov 1, 2024 · 41:02

Anastasios and Weilin from LM-Sys explain how ChatBot Arena became the de facto standard for LLM benchmarking by replacing static benchmarks with dynamic human preference evaluations. They trace the origin from Vicuna fine-tuning to the viral launch in April 2023, where anonymous side-by-side battles let the community decide which model is better. To address biases like length preference, they developed Style Control, a logistic regression method that adjusts for confounders such as response length and markdown formatting. They address the controversy around labs testing multiple private models, arguing that selection bias is empirically small and the live benchmark self-corrects over time. They also discuss RouteLLM for cost-performance routing, the graduation of ChatBot Arena from LMSys to support new projects, and call for community help with red teaming, vision modalities, and implementing a REPL for coding evaluations.

Building the Silicon Brain - Drew Houston of Dropbox

Oct 18, 2024 · 1:11:40

Drew Houston, CEO of Dropbox, details his hands-on AI engineering journey and the company's strategic pivot to AI-first products like Dropbox Dash for universal search and access control. Having spent over 400 hours coding with LLMs, he built personal tools that seeded Dropbox AI, including a file question-answering system. He advocates 'rent, don't buy' for AI infrastructure, relying on open-source models and keeping options open as costs drop 10-100x yearly. Houston explains Dropbox's advantage in trust and data privacy, positioning it as a neutral platform that integrates with Google Drive and OneDrive. He discusses staying relevant through constant learning and founder mode, and advises founders to systematically train skills ahead of their company's growth.