DeepSeek-V2, every mention

6 scenes, the whole family · ← back to DeepSeek-V2

tap a year for its mentions
002233202420252026episodesmentions
023202420252026episodes it came up in
0011.523202420252026episodesmentions per episode

every year anyone Ethan He 2Yining Zhang 1William Beauchamp 1Shawn Wang 1Ronak Malde 1

Verbatim, from the transcripts: the passages where DeepSeek-V2 comes up

loading…

⚡️Every product of the future will be a living system — Ronak Malde, Trajectory.ai Jun 21, 2026 · 1 mention

  • ▶ 14:20 Ronak Malde And you had like some Quen models, you had DeepSeq two, and it just like didn't seem promising.

Outlasting Noam Shazeer, Crowdsourcing Chai AI w/ 1.4m DAU — with William Beauchamp, Chai Research Jan 26, 2025 · 1 mention

DeepSeek V3, SGLang, and the state of Open Model Inference in 2025 (Quantization, MoEs, Pricing) Jan 19, 2025 · 1 mention

  • ▶ 27:23 Yining Zhang Something like DeepSeq V-II, they proposed attention parent named MLA, multi-latent attention, and I think SGLAN is the only framework to support that.

2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents Jan 1, 2025 · 1 mention

  • ▶ 1:17:43 Shawn Wang Um, and I think what you're starting to see now, uh, in July is the emergence of four O mini and deep sea V two as outliers to the July frontier where July frontier used to be maintained by four O Lama four five.

[Paper Club] Upcycling Large Language Models into Mixture of Experts Oct 29, 2024 · 2 mentions

  • ▶ 11:09 Ethan He For example, the DeepSeq V-II MOE, it has one 60 experts and eight of, eight of them are active.
  • ▶ 28:10 Ethan He For example, the, the Queen, Queen V-II use 64 experts, and DeepSecret II use one 21 28, or one sixty-something experts.
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes 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.