![Groq](/img/default-banner.jpg)
- Видео 119
- Просмотров 702 920
Groq
США
Добавлен 27 авг 2019
Groq is fast AI Inference.
Groq LPU™ AI inference technology delivers exceptional compute speed, quality, and energy efficiency. Groq, headquartered in Silicon Valley, provides cloud and on-prem inference at scale for AI applications. The LPU and related systems are designed, fabricated, and assembled in North America. Learn more and try Groq speed today at groq.com.
Groq LPU™ AI inference technology delivers exceptional compute speed, quality, and energy efficiency. Groq, headquartered in Silicon Valley, provides cloud and on-prem inference at scale for AI applications. The LPU and related systems are designed, fabricated, and assembled in North America. Learn more and try Groq speed today at groq.com.
Code Interpreting with LLMs Powered by Groq & E2B Sandboxes
This is a recording of a technical webinar held by Groq and E2B on September 3rd, which covers the use of E2B code interpreter with models powered by Groq.
In this session, we will show practical examples of running LLM-generated code in the secure E2B cloud sandbox, controlled with the open-source E2B Code Interpreter SDK.
Our focus will be on data analysis and advanced reasoning tasks, and we'll leverage Groq LPU™ AI inference technology for instant code generation.
Join us for this webinar if you are:
- Building an AI product
- A developer or just generally technical
- Curious about getting more out of LLMs
We are happy to answer your questions and chat about your use case.
Groq API Cookbook:...
In this session, we will show practical examples of running LLM-generated code in the secure E2B cloud sandbox, controlled with the open-source E2B Code Interpreter SDK.
Our focus will be on data analysis and advanced reasoning tasks, and we'll leverage Groq LPU™ AI inference technology for instant code generation.
Join us for this webinar if you are:
- Building an AI product
- A developer or just generally technical
- Curious about getting more out of LLMs
We are happy to answer your questions and chat about your use case.
Groq API Cookbook:...
Просмотров: 733
Видео
CEO Catch Up: Past, Present & Future at Groq
Просмотров 1,4 тыс.17 часов назад
Join Mark Heaps for a brief chat with Jonathan Ross, CEO & Founder of Groq, to discuss continuous growth, iteration and innovation, and our mission to make AI accessible to everyone. We reaffirm our goal of providing free tokens to Developers and why Groq is committed to that as part of our vision. We'll address exciting new possibilities as Groq enables multimodal models, relish in the competi...
Overcoming the Challenges of Building Agentic AI
Просмотров 1,2 тыс.14 дней назад
Join Daniele Bernardi, CEO of Toolhouse AI and Dan Loman, Data and AI Practitioner at Groq for a technical webinar on the challenges of building agentic AI. They'll provide a high level overview of agentic architecture, highlight the current challenges of building agents (including building tools, prompting, and latency), explain how you can overcome them with Toolhouse AI and Groq, and share a...
Insights from VB Transform 2024 with Jonathan Ross, Groq CEO & Founder
Просмотров 40528 дней назад
Join Matt Marshall, CEO and Editor-in-Chief of VentureBeat, as he conducts a fireside chat with Jonathan Ross, CEO and founder of Groq, at VentureBeat Transform 2024. In this exclusive interview, Ross shares the Groq story, demonstrates the power of Groq Speed with an interactive voice-to-text GroqChat demo, and more. #VentureBeatTransform2024 #Groq #AIInference #LanguageProcessingUnit #AIatScale
Conquering Hallucinations - Validating AI generated Code
Просмотров 1,1 тыс.Месяц назад
Join Weights & Biases and Groq for a technical webinar on addressing one of the most prevalent challenges in AI-assisted coding: hallucinations and outdated code generation. In this session, we'll explore practical strategies for validating AI-generated code using W&B's LLMOps tooling, Weave, and Groq's optimized inference capabilities. Our focus will be on implementing robust testing framework...
Tool Calling with Groq & CrewAI
Просмотров 8 тыс.Месяц назад
Want to learn how to build AI agents for real use cases easily? Tune in to our webinar to learn how to use Groq API to power your workflows with CrewAI. We'll share demos and answer your questions.
Daily & Groq: Real-time AI Enterprise Voice Workflow - Patient Intake Use Case on Llama 3.1 405B
Просмотров 5 тыс.Месяц назад
We are proud to be partnering with @DailyHQ on the launch of a real-time voice AI demo running on Llama 3.1 405B by Meta! See what voice-to-voice can do for healthcare use cases like patient intakes in this short demo. To build with the new RTVI open standard for voice AI supported by Daily & Groq visit: git.new/ai Learn more about Daily: www.daily.co/
Groq Builds the World's Fastest AI Inference Technology
Просмотров 1,2 тыс.Месяц назад
This is recording of a session at 2024 SixFive Summit: AI Unleashed. Daniel Newman (CEO, The Futurum Group; Chief Analyst, Futurum Research; Co-Host, The Six Five Podcast and The Six Five Summit) spoke to Jonathan Ross (CEO & Founder of Groq) about how Groq technology transforms the generative AI infrastructure; how Groq’s LPU delivers speed, quality, and energy efficiency; and what augmenting ...
Groq Cloud is Changing the Rules of the Game in Generative AI
Просмотров 809Месяц назад
This is recording of a session at 2024 SixFive Summit: AI Unleashed. Dave Nicholson (Chief Research Officer, The Futurum Group) spoke to Sunny Madra (GM of GroqCloud) about the AI age and the unchanging need for compute at the fastest speed and lowest cost. For more recordings from the SixFive Summit, go to www.techstrongevents.com/the-six-five-summit-2024
Chief Technology Evangelist Mark Heaps at Imagine AI Live 2024
Просмотров 1,4 тыс.4 месяца назад
Groq Chief Tech Evangelist, Mark Heaps, is passionate about democratizing AI to advance human agency and loves exploring how end-users of the next generation of technology will interact with conversational AI. The is a recording of Mark as a featured speaker at #ImagineAILive (www.imagineai.live/), presenting about powering Generative AI with our LPU™ Inference Engine, which is better, faster a...
RAISE Fireside Chat with Jonathan Ross & Chamath Palihapitiya
Просмотров 6 тыс.4 месяца назад
At their R.AI.SE Summit fireside chat, Jonathan Ross, CEO & Founder of Groq, and Chamath Palihapitiya, CEO & Founder of Social Capital, discussed cutting-edge GenAI applications, which are setting new benchmarks for operational efficiency, product development & customer engagement. For more info on the summit: www.raisesummit.com/ Join the Groq Discord community at discord.gg/groq where you'll ...
Real-time AI Genome Processing - Powered by Groq
Просмотров 2,5 тыс.4 месяца назад
Real-time AI Genome Processing - Powered by Groq
Let's Chat with GroqChat - Where is AI going to take your business?
Просмотров 1,3 тыс.5 месяцев назад
Let's Chat with GroqChat - Where is AI going to take your business?
Writing code with Mixtral 8x7B - Iterating Fast
Просмотров 6 тыс.5 месяцев назад
Writing code with Mixtral 8x7B - Iterating Fast
Making AI real with the Groq LPU inference engine
Просмотров 6 тыс.6 месяцев назад
Making AI real with the Groq LPU inference engine
Jonathan Ross at Web Summit Qatar
Просмотров 4,5 тыс.6 месяцев назад
Jonathan Ross at Web Summit Qatar
Groq's AI Chip Breaks Speed Records
Просмотров 153 тыс.6 месяцев назад
Groq's AI Chip Breaks Speed Records
Large Language Model Speed Showdown - Bunker BBQ Sous Chef
Просмотров 2 тыс.7 месяцев назад
Large Language Model Speed Showdown - Bunker BBQ Sous Chef
Extending LLMs - RAG Demo on the Groq® LPU™ Inference Engine
Просмотров 51 тыс.7 месяцев назад
Extending LLMs - RAG Demo on the Groq® LPU™ Inference Engine
Large Language Model Speed Showdown - Gift Guides In Seconds
Просмотров 7797 месяцев назад
Large Language Model Speed Showdown - Gift Guides In Seconds
Monarch Matrices & Structured Matrices presented by Chris Smith
Просмотров 22 тыс.7 месяцев назад
Monarch Matrices & Structured Matrices presented by Chris Smith
Mixtral 8X7B Crazy Fast Inference Speed
Просмотров 83 тыс.7 месяцев назад
Mixtral 8X7B Crazy Fast Inference Speed
AI Image Styling on Groq - Crazy Fast Low Latency
Просмотров 89 тыс.8 месяцев назад
AI Image Styling on Groq - Crazy Fast Low Latency
@groq Is there a link to this specific demo that we can test?
I see a veil, i downvote ... STOP MUSLIM PROPAGANDA !
Hate disguised as 'opinions' only fuels ignorance. The veil represents personal freedom, not propaganda. Attacking a religion won’t solve your problems-it only exposes your own intolerance.
Adams Isle
tyvm!
Talking about natural dialog. Have you tried the Cerebras Voice? It's insane
You guys are amazing. thanks so much for groq and your generosity in providing so much tokens for free!
Wow the multimodal is the crazy part of this video! Cannot wait for this
We launched Llava today (blog post here: groq.link/llava). Try it out for yourself at console.groq.com.
Bruh why can't I pay you so I can use it with confidence? Awaiting the rug pull. If cerebas offers a plan I'm going with them. PAY ATTENTION
25 Million Tokens!!
when will the 405B is comming
We're holding back on making 405B available for now and dedicating all of that HW to 70B and 8B instances. We'll have a lot more HW coming later this year, in which case we'll make it available to close partners.
I am trying to reach your sales team for GroqRack™ , & Enterprise plan , I need details so I can quote my privacy concerned customers .
Reach out to sales@groq.com
There should be a team of LPUs for each step of a process like how hand-offs work just way faster so it looks like it's not separate.
Team up with Cerebras.
Lol
Carter Harbors
You said LLMs are nondeterministic. I know how to make them deterministic. I've cracked the code. Contact me if you want to know how.
You lost me when you said BBC is a trusted source
its 2024....what do you think vision transformers ruling?
Another great video
Please keep making these videos!! This is exactly what I was hoping for
Building agentic AI can be complex. Explore alternative tools to overcome challenges and optimize your development process. #AIAgents #Innovation
Great work!! Just wanted to know is the source code publicly available. Really excited to see how it was implemented
This is really great, but I believe it would be much more effective if there were an in-built option to select the most probable tools for the current situation and keep only those in context. Rationale: In my current application, I have around 15 tools, and sending all of them to the LLM for each call is not optimal. This approach quickly hits the token limit imposed by Groq within just a few seconds of running a conversational AI.
We're releasing functionality to exactly overcome the issues you describe. This functionality will allow the LLM to work with just a subset of all your installed tools, based on the task at hand. For example, if you are building a financial analyst app with two steps (retrieval and forecasting), you can feed just a the retrieval tools to the first step and just the forecasting tools to the second. This functionality is coming very soon - make sure to sign up and check out Toolhouse in the next coming days for an update!
This is what you get hiring uneducated people in the media?...you at least do some research on A.I. before the interview and knowing the difference between hardware and software 😂😂😂..
Nothing has been linked
Amazing !!!
Amazing Groq is fast and runs Llama 3.1 ( Meta AI ) , try it out
WHen might we be able to test the demo app?
It was a fun demo I conceived with the team some time ago. I really hope in the next two quarters they'll allow us to put it back up.
Great. As a musician in anxious to try it
Where oh where might we find this impressive notebook file link @GroqInc ? Forever grateful to you and the team!
Please link the notebooks in the description.
This is great now make it less aggressive and friendlier
so much problems with tool calling
This is awesome! Can we please get a link to the notebook?
Can you convince me to use CrewAI instead of LangGraph with API calls to LLMs and expert systems? I'm concerned about being too limited with CrewAI. Working on an iterative RAG workflow, sort of reasoner for an engineering application. Thoughts?
The best team right there! Absolutely love the crew AI framework + groq lpu speed + llama 3.1 405B open source models! The main limiting factors are stringent rate limits and the super small / limited input and output token limits let's do what chat gpt did with 60,000 tokens in and out per call! That would be truly game changing and launch open source above open AI gpt 4o once and for all! (Greater token & rate limits in and out are what will allow agentic workflows to truly work correctly and as intended for complex processes and architectures. Right now crewAI is great for simple tasks but for longer multi step and complex processes it will need large token limits and ideally limited rate limits!) As always great work team! 😎 🚀 👏🏻👏🏻
Awesome demo! im waiting for that link for jupyter notebook. please share it ! thank you!
yes link would be great!
# nice
Best multi agent framework is agency swarm. Why would you make a presentation with hallucinations to promote the product? Haha
When will llama 3.1 405B will be available on groq ?
Groq has incredible inference performance, but I have run into issues with it reliably outputting JSON, which model/LLM with Groq do you recommended for reliable JSON formatted outputs? For multi-step reasoning/chains/agent graphs, I normally have each previous step, output a JSON that feeds into the next step, for the whole chain/graph to not break I need each step doing an LLM call via Groq API, to reliably output JSON.
Actually, figured that using Mixtral "mixtral-8x7b-32768" as the model with Groq produces reliable JSON outputs. I was using LLama earlier. But as a user, I want to be able to use the latest models such as LLama 3.1 as well and get those to output JSON reliably.
Is webinar code publicly available somewhere on github maybe?)
Yes, I would like to know this also, specifically the Crew AÍ demo..
The problem I have with crew abs groq combo is the timeout limits
Is this using YOLOv1?
Matt on the Groq channel? Hell yeah!
Groq is super cool! Good documentation and straightforward UX. I am using the API on daily bases as a VSCode and Inteliij provider for Continue. Insanely fast. Consider to use it as a main provider in the SAAS app, I am currently building. Success to both Groq and Crew AI
How are u dealing with free rate limit
am i the only one that was 100% sure that Joao was Graham all this time ??
can I just have a form to fill out?
I want to buy that for my house for homeuse
Great tutorial! I was excited when I saw Groq was offering tool calling and I always see the “stock ticker” examples, but I’m glad to see some good examples of sequential tool calling. Definitely more “agentic”
This is amazing!!
Speed matters like hell