Empowering the next wave of AI with @AMD Instinct™ GPUs 🌊
Las Vegas, NV
- Tweets 1,239
- Following 1,484
- Followers 3,132
- Likes 1,974
Pinned Tweet
The next generation of AI infrastructure is coming to TensorWave.
TensorWave is expanding our all-AMD AI cloud with the AMD Helios rackscale solution, powered by AMD Instinct™ MI455X GPUs.
Built for frontier-scale inference, training, and fine-tuning, Helios brings @AMD compute, memory, networking, and ROCm™ software together in an open, rack-scale platform designed to deliver the performance and economics AI workloads demand.
The future of AI needs better infrastructure. We’re building it with AMD.
Read the full announcement:
tensorwave.com/blog/tensorwa…
5
1
19
2,144
We’re turning up the volume on the conversations shaping AI.
Introducing wavesession, your new go-to podcast for the ideas, breakthroughs, and big decisions around AI and technology.
Founders, researchers, builders, and investors get into the big bets, tough calls, and messy realities of building open AI infrastructure. What’s working? What’s breaking? What happens next? And most importantly, how the boundaries are being pushed...
We’re kicking things off with a big question: what happens when AI’s ambitions meet the limits of the power grid? @jtatarchuk and @ilyatabakh dig in
Stay tuned to hear from industry leaders like...
@SebastianThrun - Founder of GoogleX, Waymo, Udacity | Jerry Ting - VP/GM of Workday AI & Agents | @olivercameron - CEO of Odyssey
First episode drops September 30. New conversations every week.
Get in early.
Subscribe on Apple Podcasts - podcasts.apple.com/us/podcas…
Spotify - open.spotify.com/show/0b0f6a…
YouTube - piped.video/BrKObIWJqog
#accelerateresponsibly
2
3
9
458
What are you building in Las Vegas?
Join us at TensorWave HQ for Las Vegas AI Builders on September 30. Meet local developers and researchers, swap ideas, and catch lightning demos from people working on everything from models and agents to the infrastructure behind them.
Want to show what you’re working on? Apply for one of three 8-minute demo slots.
📅 September 30, 6–8 PM
📍 Las Vegas (address shared after registration)
RSVP: luma.com/1r74lsl2
1
2
4
357
Better AI on your phone starts with how the model is built.
At TensorWave’s Beyond Summit, @liquidai Co-Founder and CTO @mlech26l explained how his team designs models around the devices that run them, balancing quality, speed, and memory use from the start.
Our latest blog explores what that means for edge AI and why small models still require serious training compute.
Read the blog → tensorwave.com/blog/edge-ai-…
Watch the presentation → piped.video/watch?v=yNzNOhhn…
1
6
408
AI’s growth comes with big questions about power. Let’s talk about them during New York Climate Week.
TensorWave’s VP of Innovation, @ilyatabakh will join speakers from Heron Power, Forge Growth Infrastructure, and @CrusoeAI for “Energy Complexity in the AI Build Out,” a morning of discussion, breakfast, and networking with people working at the intersection of AI and energy.
📅 Tuesday, September 22 | 8:30–10:30 AM
📍 New York, NY
Hosted by Primary Venture Partners, Reveille VC, Newlab, and Baker Tilly US.
Register here: partiful.com/e/Kz4Rw40S4ZA0v…
3
3
276
Two cities. One evening. A whole lot of builders.
On September 30, TensorWave is bringing the community together in Las Vegas and San Francisco. Bring your projects, your questions, and that idea you’ve been meaning to try.
📍 Las Vegas AI Builders | TensorWave HQ
Meet local developers, swap ideas, and catch lightning demos over light bites. Want to show what you’re building? Apply for one of three 8-minute demo slots.
6–8 PM | Request to join: luma.com/1r74lsl2
📍 Late Night C.H.I.P Sessions | San Francisco
Grab your laptop and settle in for an evening of coffee, coding, and conversation with fellow builders at Corgi Cafe. Hosted in partnership with Corgi Cafe.
Event full | Join the waitlist: luma.com/1e1oigq1
2
4
322
AI compute is a technology decision. It’s also a business decision.
Join TensorWave President & COO @piotrstomasik at Yotta 2026 for “Benchmarks vs Balance Sheets: Who Really Decides the Future of AI Compute?” to explore how performance and financial priorities shape what gets built.
📅 September 29 | 11:40 AM–12:25 PM
📍 Caesars Forum, Las Vegas
See you there.
More info here: yotta-event.com/benchmarks-v…
1
2
231
Vegas, we’ll see you at Yotta.
Catch TensorWave CEO and Co-Founder Darrick Horton 🌊 onstage for the "Investing In Infrastructure" Keynote at Yotta 2026.
Join us for a conversation about investing in the infrastructure behind AI’s next wave.
📍 Caesars Forum, Las Vegas
📅 September 28–30
#AccelerateResponsibly
1
7
273
Power, capacity, and the pressure to build faster. There was plenty to talk about at Datacloud USA 2026.
Our team joined conversations on bringing compute online faster and designing data centers that can adapt as AI workloads evolve.
Thanks to everyone who connected with us and shared their perspective.
#AccelerateResponsibly
1
2
6
483
Keep the Yotta conversations going over cocktails.
Join TensorWave, ByteBridge, Inova, @ServerLIFT, and @AriaNetworks, for an evening with the people behind AI infrastructure.
Grab a drink, meet a few new faces, and talk GPUs, data centers, and whatever else comes up.
September 28 | 6–9 PM
Space is limited, so request your invitation: luma.com/nw8zgltp?utm_source…
2
1
287
Train larger models and process more data by spreading the work across GPUs and machines.
Our latest blog explores five benefits of distributed computing for AI, from faster training to fault recovery and better use of GPU resources.
Read the blog: tensorwave.com/blog/5-ways-d…
1
1
7
267
Keep your team focused on training models, running simulations, and analyzing results.
TensorWave Managed Slurm pairs GPU compute with the expertise to manage your cluster, helping you run HPC and AI workloads while reducing the need to hire specialized infrastructure staff.
You bring the workload. We handle the cluster.
tensorwave.com/products/mana…
1
1
3
251
Adam Kahn, Director of Strategic Finance & FP&A at TensorWave, shares what it takes to meet the growing infrastructure and compute demands behind AI at Datacloud USA 2026.
2
6
485
Proud to have been part of this!
AI inference is about more than peak throughput.
Independent @Signal_65 testing shows AMD Instinct MI355X led 2 of 3 models tested and delivered 1.42×–2.15× tok/$ across all 3, even on Kimi-K2.6, where the competition led median throughput. Testing was hosted via @tensorwave. Read more ↓ bit.ly/45hAvl3
ALT Promotional image featuring the text "AMD Instinct MI355X delivers competitive throughput with leading perf/$." The AMD logo and tagline "together we advance" are at the bottom. The background has dynamic blue wave patterns.
ALT The image is a promotional graphic for a financial analysis of GPT-OSS-120B. It highlights a 1.3 times higher throughput and 53% lower cost per document. The source is noted as Signal65, July 2026.
ALT A promotional graphic titled "Long Report Generation KIMI-K2.6" features bold text indicating "0.96X Competitive Throughput" and "1.42X More Tokens/$." The source cited is "Signal65, July 2026." The design includes dynamic blue and turquoise digital waves on a black background.
ALT The image is a promotional graphic for "Interactive RAG Chat QWEN3-NEXT-80B." It highlights two key features: "1.2x higher throughput" and "2x more users at SLA." The source is Signal65, dated July 2026. The design includes a black background with blue digital wave patterns.
1
18
986
At Datacloud USA 2026, TensorWave VP of Innovation Ilya Tabakh discusses what it takes to build AI infrastructure in an environment where power has become a critical constraint.
2
6
343
A few highlights from Datacloud USA
TensorWave’s Co-founder and President @piotrstomasik joined industry leaders to discuss what it takes to build and operate AI-ready data centers as infrastructure demands continue to evolve.
From power and cooling to flexibility and reliability, the conversation focused on the systems behind the next generation of AI infrastructure.
Catch a few moments here...
3
9
415
Something has changed in our conversations...
We're spending less time answering, “Why AMD?” and more time answering, “What can we build on it?”
That’s an important shift.
Developers have more tools, more software support, more hardware options, and more reasons to evaluate AMD on its own merits.
The conversation isn't about proving AMD belongs in AI anymore... It's about what's possible when you build on it.
Check out our AMD-exclusive AI cloud tensorwave.com
3
20
660
TensorWave retweeted
Josh O’Brien of @TensorWave will join our co-founder Salil Jani at NetBox Evolve for a fireside chat on what it takes to scale infrastructure at AI speed, from rapid GPU growth to automation.
Join us at Kennedy Space Center on October 13: hubs.ly/Q04w5RlX0
3
3
199
TensorWave retweeted
Another Daytona AI Builders in San Francisco is behind us! 🚀
Huge thanks to our event partners, @descopeinc & @tensorwave, our amazing speakers @MrunankPawar, @evisdrenova, @zhuolunfranklin, @LinghuaJ, @muhashmii, and everyone who joined us and made the night special.
We’ll be back on September 29 for another monthly AI Builders Demo Night in SF. More details coming soon.
See you there!
5
17
2,120
As GPU clusters grow, managing #Slurm gets more complex.
Here are five reasons AI teams are turning to managed Slurm to reduce overhead and get more from their infrastructure.
Read more ↓
tensorwave.com/blog/5-benefi…
1
6
374