DeepSeek-V2 episode artwork

EPISODE · Feb 10, 2025 · 10 MIN

DeepSeek-V2

from Large Language Model (LLM) Talk · host AI-Talk

DeepSeek-V2 is a Mixture-of-Experts (MoE) language model that balances strong performance with economical training and efficient inference. It uses a total of 236B parameters, with 21B activated for each token, and supports a context length of 128K tokens. Key architectural innovations includeMulti-Head Latent Attention (MLA), which compresses the KV cache for faster inference, andDeepSeekMoE, which enables economical training through sparse computation. Compared to DeepSeek 67B, DeepSeek-V2 saves 42.5% of training costs, reduces the KV cache by 93.3%, and boosts maximum generation throughput by 5.76 times. It is pre-trained on 8.1T tokens of high-quality data and further aligned through Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL).

Episode metadata supplied by the publisher feed · Published Feb 10, 2025

DeepSeek-V2 is a Mixture-of-Experts (MoE) language model that balances strong performance with economical training and efficient inference. It uses a total of 236B parameters, with 21B activated for each token, and supports a context length of 128K tokens. Key architectural innovations includeMulti-Head Latent Attention (MLA), which compresses the KV cache for faster inference, andDeepSeekMoE, which enables economical training through sparse computation. Compared to DeepSeek 67B, DeepSeek-V2 saves 42.5% of training costs, reduces the KV cache by 93.3%, and boosts maximum generation throughput by 5.76 times. It is pre-trained on 8.1T tokens of high-quality data and further aligned through Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL).

PodParley-generated summary based on available episode metadata and transcript content.

NOW PLAYING

DeepSeek-V2

0:00 10:39

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Humanizing Change Tremendousness Join us each episode as we talk with innovators in their respective fields about their unique journeys and how they humanize change in their own work, right here, on Humanizing Change. AI Erik's Podcast Audio Erik Conn The AI News Podcast where we talk AI. NEWMORROW SESSIONS - A PodCast Series on the Future of Hospitality Mario C. Bauer, Florian Schneider, Axel Weber & Dr. Tillman Bardt The Newmorrow PodCast is more than a podcast — it's a platform for open dialog on the future of our business, a platform for those building what doesn’t exist yet. Here, we share and embrace our passion for the hospitality industry, but we won’t romanticize the journey. We ask the tough questions, confront uncomfortable truths, and prepare for a future that resists easy answers. We believe that the tougher and wilder times become, the more openly, honestly and humanely people need to talk to each other and act together. We believe, openness, togetherness, and truthfulness should also be cornerstones of a professional community to develop our utopian idea of „open source“. This is a space where visionaries don’t just imagine the future — they wrestle with the paradoxes that shape it: success vs. happiness, data vs. instinct, stability vs. reinvention. Join leaders, entrepreneurs, and thinkers as they share not what made them — but what’s actively shaping them, now and next. So tune in Hyperfluent Hypio Hyperfluent transmits straight from the heart of Hyperliquid, where culture, creativity, and capital converge. Anchored by the architects of Hypio—the decentralized cultural virus—each episode archives the minds engineering the blockchain built to house all finance. These conversations are traceable artifacts in HyperEVM’s evolution: not just what’s being built, but why it matters, how it mutates, and where it’s taking us next. Listen in for the blueprints, the blind spots, and the narrative weapons shaping tomorrow’s markets.Hyperfluent: learn the language, ride the wave, spread the strain.

Frequently Asked Questions

How long is this episode of Large Language Model (LLM) Talk?

This episode is 10 minutes long.

When was this Large Language Model (LLM) Talk episode published?

This episode was published on February 10, 2025.

What is this episode about?

DeepSeek-V2 is a Mixture-of-Experts (MoE) language model that balances strong performance with economical training and efficient inference. It uses a total of 236B parameters, with 21B activated for each token, and supports a context length of 128K...

Can I download this Large Language Model (LLM) Talk episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!