Загрузка видео...

Не удалось загрузить видео

На главную

Everyone talks about our hardware @Cerebras. Few notice the software. Ryan Loney breaks down the hidden optimizations powering 20× faster LLM inference than GPUs, speculative decoding, token reuse, and why we’re just getting started. Watch the full story here

cerebras's profile picture

Cerebras

59,159 subscribers

222,816 просмотров • 7 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🚨 Cerebras Inference is now 3x faster: Llama3.1-70B just broke 2,100 tokens/s - 16x faster than the fastest GPU solution - 8x faster than GPUs running Llama *3B* - It's like the perf of a new hardware generation in a single software release Available now at
0:26

🚨 Cerebras Inference is now 3x faster: Llama3.1-70B just broke 2,100 tokens/s - 16x faster than the fastest GPU solution - 8x faster than GPUs running Llama *3B* - It's like the perf of a new hardware generation in a single software release Available now at

Cerebras

236,142 просмотров • 1 год назад

Introducing Cerebras Inference ‣ Llama3.1-70B at 450 tokens/s – 20x faster than GPUs ‣ 60c per M tokens – a fifth the price of hyperscalers ‣ Full 16-bit precision for full model accuracy ‣ Generous rate limits for devs Try now:
0:21

Introducing Cerebras Inference ‣ Llama3.1-70B at 450 tokens/s – 20x faster than GPUs ‣ 60c per M tokens – a fifth the price of hyperscalers ‣ Full 16-bit precision for full model accuracy ‣ Generous rate limits for devs Try now:

Cerebras

707,624 просмотров • 2 лет назад

🎂 Cerebras Inference turns 1! 🚀 Let's break it down: - 6x faster than when we launched — From Meta Llama to Qwen 3 to OpenAI OSS, models running on Cerebras deliver 𝟯,𝟬𝟬𝟬+ 𝘁𝗼𝗸𝗲𝗻𝘀/𝘀𝗲𝗰 - Our inference powers the best AI natives, global enterprises, and developers including Meta, IBM , AlphaSense, Docker, GSK , Mayo Clinic, Core42, Vercel and more - Largest model served: ~half a trillion parameters, 7x bigger than launch - #1 provider of tokens on Hugging Face 🤗 - Serving billions of tokens per day on - The leading code gen inference provider, powering AI developers with Cline and Windsurf (retired) We’re just getting started… but couldn’t have done Year 1 without YOU. Build on, builders. ❤️‍🔥
0:39

🎂 Cerebras Inference turns 1! 🚀 Let's break it down: - 6x faster than when we launched — From Meta Llama to Qwen 3 to OpenAI OSS, models running on Cerebras deliver 𝟯,𝟬𝟬𝟬+ 𝘁𝗼𝗸𝗲𝗻𝘀/𝘀𝗲𝗰 - Our inference powers the best AI natives, global enterprises, and developers including Meta, IBM , AlphaSense, Docker, GSK , Mayo Clinic, Core42, Vercel and more - Largest model served: ~half a trillion parameters, 7x bigger than launch - #1 provider of tokens on Hugging Face 🤗 - Serving billions of tokens per day on - The leading code gen inference provider, powering AI developers with Cline and Windsurf (retired) We’re just getting started… but couldn’t have done Year 1 without YOU. Build on, builders. ❤️‍🔥

Cerebras

35,218 просмотров • 1 год назад

After 9 years at NVIDIA, James Wang left and joined Cerebras. In this Big Chip Club episode, James Wang breaks down the bottlenecks of NVIDIA GPUs, and what's keeping them OUT OF first place... Drop your follow-up questions below 👇
1:24

After 9 years at NVIDIA, James Wang left and joined Cerebras. In this Big Chip Club episode, James Wang breaks down the bottlenecks of NVIDIA GPUs, and what's keeping them OUT OF first place... Drop your follow-up questions below 👇

Cerebras

411,916 просмотров • 9 месяцев назад

Fully homomorphic encryption was invented in the 1980s. Why wasn't it adopted sooner? A 100,000x slowdown, driven by memory boundedness. Ajay Joshi from CipherSonic AI explains how his team got it down to less than 2x. (if this pattern sounds familar... LLM inference is memory-bound too. It's why wafer-scale exists.)
2:12

Fully homomorphic encryption was invented in the 1980s. Why wasn't it adopted sooner? A 100,000x slowdown, driven by memory boundedness. Ajay Joshi from CipherSonic AI explains how his team got it down to less than 2x. (if this pattern sounds familar... LLM inference is memory-bound too. It's why wafer-scale exists.)

Cerebras

57,817 просмотров • 3 месяцев назад

The Fastest AI Just Got Faster. Meet CS-4.
1:08

The Fastest AI Just Got Faster. Meet CS-4.

Cerebras

1,491,962 просмотров • 15 дней назад

NVIDIA paid $20B for Groq. AWS partnered with Cerebras for the same purpose. A quick breakdown of why disaggregated inference is the next thing in AI infrastructure.
1:06

NVIDIA paid $20B for Groq. AWS partnered with Cerebras for the same purpose. A quick breakdown of why disaggregated inference is the next thing in AI infrastructure.

Cerebras

383,458 просмотров • 2 месяцев назад

gpt-oss-120b is one of the most-used models on Cerebras Inference. We sat down with Anastasios Nikolas Angelopoulos from Arena.ai and @SarahChieng to break down its strengths, weaknesses, and where it's outperforming. Here's what he's seeing.
2:46

gpt-oss-120b is one of the most-used models on Cerebras Inference. We sat down with Anastasios Nikolas Angelopoulos from Arena.ai and @SarahChieng to break down its strengths, weaknesses, and where it's outperforming. Here's what he's seeing.

Cerebras

13,076 просмотров • 5 месяцев назад

In pick the best model > improve your prompts > catch bugs with Braintrust and Cerebras inference. Avoid the AI deleting your entire codebase this halloween and remember, our free tier gets you 1M+ free toks/day per model.
1:16

In pick the best model > improve your prompts > catch bugs with Braintrust and Cerebras inference. Avoid the AI deleting your entire codebase this halloween and remember, our free tier gets you 1M+ free toks/day per model.

Cerebras

299,029 просмотров • 10 месяцев назад

Introducing the Cerebras Ambassador Program 🌏 We're looking for AI community builders to build your local ecosystem around the world's fastest inference. In the last few months, our community has hosted Cafe Compute Meetups in Berlin, Mexico City, Mumbai, SF, Seattle, and NYC. We want your city to be next! Application link in comments.
0:48

Introducing the Cerebras Ambassador Program 🌏 We're looking for AI community builders to build your local ecosystem around the world's fastest inference. In the last few months, our community has hosted Cafe Compute Meetups in Berlin, Mexico City, Mumbai, SF, Seattle, and NYC. We want your city to be next! Application link in comments.

Cerebras

102,053 просмотров • 2 месяцев назад

📣 ANNOUNCEMENT DAY AT CEREBRAS 📣 Today, we are thrilled to share some of the biggest announcements in our company’s history. 📢 Cerebras announces CS-3, the world’s fastest AI Chip with a whopping 4 trillion transistors 📢 Cerebras selects Qualcomm to deliver unprecedented performance in AI Inference 📢 Cerebras and G42 break ground on Condor Galaxy 3, an 8 exaFLOPs AI Supercomputer Read all about it! 📰 CS-3 Press Release: 📰 Cerebras + Qualcomm Press Release: 📰 Condor Galaxy 3 Press Release: #AI #Supercomputer #ExaFLOPs #ML #Training #Inference
1:17

📣 ANNOUNCEMENT DAY AT CEREBRAS 📣 Today, we are thrilled to share some of the biggest announcements in our company’s history. 📢 Cerebras announces CS-3, the world’s fastest AI Chip with a whopping 4 trillion transistors 📢 Cerebras selects Qualcomm to deliver unprecedented performance in AI Inference 📢 Cerebras and G42 break ground on Condor Galaxy 3, an 8 exaFLOPs AI Supercomputer Read all about it! 📰 CS-3 Press Release: 📰 Cerebras + Qualcomm Press Release: 📰 Condor Galaxy 3 Press Release: #AI #Supercomputer #ExaFLOPs #ML #Training #Inference

Cerebras

128,618 просмотров • 2 лет назад

Our coding workflows were designed to accommodate slow inference. OpenAI's Codex Spark powered by Cerebras changes the game. Here's how we make the most out of 1,200 tokens per second, with Sarah Chieng.
5:26

Our coding workflows were designed to accommodate slow inference. OpenAI's Codex Spark powered by Cerebras changes the game. Here's how we make the most out of 1,200 tokens per second, with Sarah Chieng.

Cerebras

13,421 просмотров • 5 месяцев назад

🟧 Cerebras Inference self-serve is finally here 🟧 – Pay by credit card starting at $10 – Run Qwen3 Coder, GPT OSS & more at 2,000+ TPS – 20x the speed of GPU-based model providers Go ahead. Melt our wafers.
0:40

🟧 Cerebras Inference self-serve is finally here 🟧 – Pay by credit card starting at $10 – Run Qwen3 Coder, GPT OSS & more at 2,000+ TPS – 20x the speed of GPU-based model providers Go ahead. Melt our wafers.

Cerebras

52,825 просмотров • 10 месяцев назад

🚨 Big news! Cerebras is launching six new AI data centers across North America & Europe. This expands our capacity to 40M+ tokens/sec, making Cerebras the first hyperscale cloud for high-speed AI inference. Read more:
0:53

🚨 Big news! Cerebras is launching six new AI data centers across North America & Europe. This expands our capacity to 40M+ tokens/sec, making Cerebras the first hyperscale cloud for high-speed AI inference. Read more:

Cerebras

27,477 просмотров • 1 год назад

Introducing SuperNinja – the world’s fastest deep research by NinjaTech AI powered by Cerebras: ‣ 1-2min for full answer instead of 10min ‣ 5x faster than o3, Gemini Pro etc. ‣ Same accuracy as measured by GAIA
0:47

Introducing SuperNinja – the world’s fastest deep research by NinjaTech AI powered by Cerebras: ‣ 1-2min for full answer instead of 10min ‣ 5x faster than o3, Gemini Pro etc. ‣ Same accuracy as measured by GAIA

Cerebras

25,541 просмотров • 1 год назад

10 academic papers. Parsed, analyzed, and synthesized. In under 10 seconds. We built a research agent with @Cerebras Inference and Unstructured that processes entire literature reviews so you become a subject expert faster
0:39

10 academic papers. Parsed, analyzed, and synthesized. In under 10 seconds. We built a research agent with @Cerebras Inference and Unstructured that processes entire literature reviews so you become a subject expert faster

Cerebras

14,654 просмотров • 6 месяцев назад

Previewing Ultrafast mode for OpenAI's GPT 5.6 Sol, powered by Cerebras. GPT-5.6 Sol Ultrafast generates responses at up to 750 tokens per second. That's the full, GPT-5.6-Sol model -- up to 14× faster than the same model on Standard processing. It speedran Humanity’s Last Exam in 11h 11m, nearly 7× faster than Claude Fable 5 with comparable accuracy.
0:46

Previewing Ultrafast mode for OpenAI's GPT 5.6 Sol, powered by Cerebras. GPT-5.6 Sol Ultrafast generates responses at up to 750 tokens per second. That's the full, GPT-5.6-Sol model -- up to 14× faster than the same model on Standard processing. It speedran Humanity’s Last Exam in 11h 11m, nearly 7× faster than Claude Fable 5 with comparable accuracy.

Cerebras

1,284,390 просмотров • 20 дней назад

OpenAI Codex-Spark powered by Cerebras You can now just build things faster—at 1,000 tokens/s.
0:47

OpenAI Codex-Spark powered by Cerebras You can now just build things faster—at 1,000 tokens/s.

Cerebras

287,784 просмотров • 6 месяцев назад

Cerebras Code: 20x faster than Claude, 1x the price Today we are launching two monthly coding plans: ➡️Cerebras Code Pro: $50/m – for indie developers ➡️Cerebras Code Max: $200/m – for power users with 5x rate limits Both plans get: Qwen3-Coder at 2,000 tokens/s, 131K context, and no weekly limits. Sign up now:
0:43

Cerebras Code: 20x faster than Claude, 1x the price Today we are launching two monthly coding plans: ➡️Cerebras Code Pro: $50/m – for indie developers ➡️Cerebras Code Max: $200/m – for power users with 5x rate limits Both plans get: Qwen3-Coder at 2,000 tokens/s, 131K context, and no weekly limits. Sign up now:

Cerebras

461,380 просмотров • 1 год назад

We're here. We're profitable (99% in Web3 can't say the same!) And we're just getting started. Ethan, COO, breaks down our goals for 2026.
1:28

We're here. We're profitable (99% in Web3 can't say the same!) And we're just getting started. Ethan, COO, breaks down our goals for 2026.

Particle Network

28,137 просмотров • 8 месяцев назад