vLLM

1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Nov 20, 2025 by Nathan Lambert · said 11 times in 2 episodes since 2024 · across every show →

Mentions by year

brought up most by Dylan Patel (8), Matt Turck (3)

tap a year for its mentions
004181202420252026episodesmentions
011202420252026episodes it came up in
0040.581202420252026episodesmentions per episode

every mention, scene by scene, with the transcript →

Everything said about vLLM, oldest first

Nov 20, 2025
Assertion Supported
Lambert: Kernel differences between vLLM and Hugging Face cause RL numerical instability
“VLLM and HuggingFace use different kernels to do the actual internal computation of the model. So these kernels are the things that make things like vLLM really fast. But these things, this then results in subtle numerical differences between the completions t…”
Nathan Lambert Nov 20, 2025 ▶ 1:15:29 Open Source AI Strikes Back — Inside Ai2’s OLMo 3 ‘Thinking"
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 400 conversations transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.