Fireworks AI’s Post

Founder and CTO at Wordware (YC S24)

Keeping up with our same-day ritual for hot new models at Wordware (YC S24) we release Gemma 2 9B from Google. Thanks to Fireworks AI for helping to make this happen, accelerated by my nudging at the AI Engineer World Fair. #llm #ai #google #gemma2

5 Comments

Mark Bain

Multifaceted polymath, serial entrepreneur, tech geek, problem solver, builder

You guys are fast!

Aditya Advani

Live Free & Fly w Gen AI

Killer hustle, was curious about how on earth to try it. Kudos

2 Reactions

Faizan Ali

CTO | Mentor | Oleologist

🚀 🚀 🚀

See more comments

To view or add a comment, sign in

More Relevant Posts

Fireworks AI

5,568 followers
4h
Report this post
Llama 3.1 8B, 70B Instruct are now available for fine-tuning. Fine-tuning guide - https://lnkd.in/ePniXSj9
Like Comment
To view or add a comment, sign in
Fireworks AI

5,568 followers
3d Edited
Report this post
Looking to run inference on state-of-the-art infrastructure? Fireworks AI is the first to offer Llama 3.1 inference using both Nvidia and AMD GPUs. We’re committed to providing the best hardware for unmatched performance and cost efficiency. With Nvidia H100 and AMD Instinct MI300X accelerators, Fireworks is perfect for developers building applications with large, complex models like Llama 3.1 405B.

Karim Bhalwani

GTM Leader at AMD, AI GPUs
4d

Thrilled to share that Meta's Llama 3.1 family of models, including 8B, 70B and 405B, runs seamlessly on AMD's AI GPUs, empowering pioneers like Fireworks AI to offer one of the fastest and most efficient inference engines from the start. We are grateful for the opportunity to leverage our advanced memory capabilities, with up to 192 GB of HBM3. This allows a server equipped with eight AMD MI300X GPUs to accommodate the entire Llama 3.1 model, with its 405 billion parameters, in a single server using the FP16 datatype. This remarkable memory capacity enables AI builders everywhere to minimize server usage, offering significant cost savings, simplifying infrastructure management, and enhancing performance efficiency.

Revolutionizing AI: Meta's New Llama 3.1 Launched with Day 0 Support on AMD Instinct ™ MI300X

community.amd.com
Like Comment
To view or add a comment, sign in
Fireworks AI

5,568 followers
4d Edited
Report this post
🚀 Exciting news! Fireworks AI is one of the first platforms to offer Llama 3.1 for production use from day one in partnership with AI at Meta. With expanded context length, multilingual support, and the powerful Llama 3.1 405B model, developers can now leverage unmatched AI capabilities. Start building today! https://lnkd.in/g7KZijbh
1 Comment
Like Comment
To view or add a comment, sign in
Fireworks AI

5,568 followers
1w
Report this post
What are Compound AI Systems? Catch up on this engaging chat from @lqiao and @hwchase17 about Compound AI, Agents, and more. https://lnkd.in/ecNuQuJU

What are Compound AI Systems? ft Lin Qiao CEO Fireworks & Harrison Chase CEO LangChain AI

https://www.youtube.com/
Like Comment
To view or add a comment, sign in
Fireworks AI

5,568 followers
2w
Report this post
"a single model is not enough" says Lin Qiao Read more about Fireworks AI and our funding announcement covered by Bloomberg https://lnkd.in/eWwyxPbK

Sequoia, Nvidia Back Startup Fireworks AI at $552 Million Valuation

bloomberg.com
Like Comment
To view or add a comment, sign in
Fireworks AI

5,568 followers
2w
Report this post
Fireworks is raising $52M, led by Sequoia Capital! "We’re using the funding to make a shift towards compound AI systems that can orchestrate across multiple models with different modalities and tools” Learn more from our live Bloomberg interview: https://lnkd.in/gW2ViFJn

Sequoia, Nvidia Back Fireworks AI

bloomberg.com

6 Comments
Like Comment
To view or add a comment, sign in

5,568 followers

View Profile Follow

Fireworks AI’s Post

More Relevant Posts

What are Compound AI Systems? ft Lin Qiao CEO Fireworks & Harrison Chase CEO LangChain AI

https://www.youtube.com/

Explore topics