AI Insights – EP.2: Unlocking Cost-Effective AI with Small Language Models

AI Insights – EP.2: Unlocking Cost-Effective AI with Small Language Models

In the latest episode of the Cisco AI Insights Podcast, hosts Rafael Herrera and Sónia Marques welcome Cisco AI operations engineer James Tidd for a discussion on the world of small language models (SLMs) and the evolution of efficient AI inference. Together, they unravel the complexities behind “Fast Inference from Transformers via Speculative Decoding,” a groundbreaking paper from Google that explores how smaller draft models can speed up large language model predictions while maintaining accuracy. James shares his hands-on experience experimenting with the technique, leveraging knowledge distillation and speculative execution. The trio also discusses the potential of this approach to optimize AI, reduce power consumption and costs, and help businesses of all sizes get more out of existing hardware. A special thank you to Google’s AI team for developing this month's paper. If you are interested in reading the paper yourself, please visit this link: https://research.google/blog/looking-back-at-speculative-decoding/.

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(500)

The evolution of good technology | Tech Unscripted

The evolution of good technology | Tech Unscripted

In this episode, industry leaders discuss how to redefine “good” technology today — weighing speed, agility and AI against security, ethics and human impact. Panelists share real examples, from digita...

14 Aug 33min

Scaling AI: The Playbook for IT Services Delivery

Scaling AI: The Playbook for IT Services Delivery

Cisco Technical Assistance Center (TAC) manages 1.4 million SRs annually, and today, 97% are touched by AI. As we shift from task-based automation to Agentic AI, some of these interactions are becomin...

14 Aug 29min

404 Script Not Found: Part 2! AI Deep Dive with Annie Hardy

404 Script Not Found: Part 2! AI Deep Dive with Annie Hardy

Back for part two of our split episode with the founder of Split Futures, Annie Hardy and jump right in where we left off...getting practical about choosing the right AI model—because apparently not e...

13 Aug 24min

404 Script Not Found: AI Deep Dive with Annie Hardy

404 Script Not Found: AI Deep Dive with Annie Hardy

Your company bought all the AI tools and now nobody knows what to do with them. Sound familiar? Kat and Ian sit down with Annie Hardy, founder and Chief AI Architect at Split Futures, to unpack why l...

11 Aug 19min

Cisco Tech Stories Season 4 Kickoff: Top Episodes & Wild Tech Tales

Cisco Tech Stories Season 4 Kickoff: Top Episodes & Wild Tech Tales

Episode 37 kicks off Cisco Tech Stories' fourth season with a highlights reel of the best episodes from the past three years. Hosts Nico and Tristan revisit standout interviews and mini‑series, sharin...

2 Aug 43min

Shaping Cisco’s Portfolio Strategy with Jeetu Patel and Jeff Schultz

Shaping Cisco’s Portfolio Strategy with Jeetu Patel and Jeff Schultz

Jeff Schultz joins Jeetu Patel to delve into the evolution of the Cisco Portfolio and how this focus on critical business outcomes for the AI era is delivering real results for the ecosystem.

30 Juli 35min

Building Future-Proofed Workplaces with Jeetu Patel and Anurag Dhingra

Building Future-Proofed Workplaces with Jeetu Patel and Anurag Dhingra

Jeetu and Anurag Dhingra explore the transformation of physical infrastructure and intelligent software as the foundation for the workplace. As the nature of work continues to evolve, the demand for e...

30 Juli 28min

Scaling AI: Enterprise Requirements of Agentic AI

Scaling AI: Enterprise Requirements of Agentic AI

95% of enterprise IT leaders plan to launch agentic AI projects — but 69% aren't ready. So, what's standing in the way?  In this episode of Scaling AI in the Enterprise, we bring together an expert p...

30 Juli 33min

Populärt inom Teknik

uppgang-och-fall
market-makers
skogsforum-podcast
rss-uppgang-och-fall
rss-laddstationen-med-elbilen-i-sverige
rss-elektrikerpodden
rss-en-ai-till-kaffet
natets-morka-sida
 och-bilen-gar-bra
bli-saker-podden
rss-veckans-ai
under-femton
hej-bruksbil
elbilsveckan
developers-mer-an-bara-kod
bosse-bildoktorn-och-hasse-p
rss-fabriken-2
garagehang
klocksnack-tillsammans-med-nymans-ur-1851
bilar-med-sladd