AMD
@AMD
together we advance_
ID:14861876
http://www.AMD.com 21-05-2008 22:14:12
10,2K Tweets
1,2M Followers
322 Following
Follow People
.The Six Five Media Patrick Moorhead & @DanielNewmanUV AMD’s Advancing AI Event w/ #CEO Lisa Su. They discuss the state of the AI market, their advancement of #AI in their product portfolio, & the launch of AMDInstinct MI300X #GPU . $AMD #TogetherWeAdvance twitter.com/i/broadcasts/1…
New from efxmarty Ilyas Moutawwakil Mohit Sharma Ella Charlaix Morgan Funtowicz at Hugging Face, AMD + 🤗: Large Language Models Out-of-the-Box Acceleration with AMD GPU
huggingface.co/blog/huggingfa…
Exascale #Supercomputing Is Coming to Stuttgart: Hunter will be based on the AMD Instinct MI300A accelerated processing unit (APU). This will slash the energy required to operate Hunter by approximately 80% at peak performance and will raise peak performance to 39 petaFLOPS.
AMD ROCm 6.0 is out, release notes: rocm.docs.amd.com/en/latest/abou…
🧮 Improved perf for lower precision math and attention layers
✨ Sparsity and quantization with DeepSpeed, ONNX-RT, CuPy plus new hipSPARSELt lib
🔥 Frameworks and ML pipeline updates for PyTorch, TensorFlow, JAX
AMD supports open standards and interoperability for AI by working with strategic networking partners like Broadcom Inc. Arista Networks and Cisco through Ultra Ethernet Consortium Consortium and opening the AMD Infinity Fabric ecosystem. Patrick J Kennedy for STH:
Take a technical deep dive with Tim Prickett Morgan as he breaks down the new AMD Instinct MI300X GPUs and AMD Instinct MI300A APUs:
Learn more about the AMD Instinct MI300 and how it was carefully designed to layer computing, memory, and communication in this breakdown from IEEE Spectrum:
Today is a very large day for AI and AMD.
Spoke with Jon Fortt, Kelly Evans, and Kristina Partsinevelos here in San Jose.
We covered the MI300x, supply challenges, market growth, and the collab/compete strategy with hyperscale cloud providers.
This isn't a one-horse race, and the…