Beyond CUDA

TensorWave

Beyond CUDA is where the future of AI infrastructure gets real. Hosted by Jeff Tatarchuk, co-founder of TensorWave, the show dives deep with the founders, developers, and investors redefining how AI is built and scaled. From bleeding-edge models to open-source breakthroughs, Jeff unpacks the tech, tactics, and people shaping what’s next—beyond the NVIDIA-dominated status quo.

Episodios

  1. Spectral Compute CEO: Running CUDA on AMD with SCALE

    27/08/2025

    Spectral Compute CEO: Running CUDA on AMD with SCALE

    Learn how Spectral’s Scale toolkit breaks CUDA’s vendor lock-in by letting you run the same code on AMD GPUs with zero rewrites. This episode shows how to future-proof your stack without starting from scratch. #GPUCloud #BeyondCUDA #TensorWave 01:05 - How did you get into GPU development? 03:39 - What is Scale? 05:35 - What are the technical hurdles? 06:34 - What are the opportunities? 07:46 - What is Spectral Focused On? 09:14 - How to break down Scale? 🌐 Connect with us: https://www.linkedin.com/in/jtatarchuk https://dk.linkedin.com/in/michaelsondergaard

    25 min
  2. Automating GPU Kernels: Mako’s CEO on Crossing the CUDA Moat

    27/08/2025

    Automating GPU Kernels: Mako’s CEO on Crossing the CUDA Moat

    Waleed Atallah from Mako joins us to discuss automating GPU kernel generation with AI. 03:07 – Why GPU kernels bottleneck progress04:46 – Three current ways to get kernels06:02 – LLMs: can they write fast kernels?07:48 – Mako’s “kernel agent” in action09:12 – Early adopters & best-fit users12:05 – Data scarcity limits fine-tuning16:18 – AI-written kernels by 2030?20:27 – Top technical risks ahead #BeyondCUDA #GPUkernels #mako 🌐 Connect with us:https://www.linkedin.com/in/jtatarchukhttps://www.linkedin.com/in/waleedatallah (00:00) - C1750 P1315 Waleed Atallah Audio (26:24) - OUTRO SEQUENCE

    26 min
  3. The True Story of ZLUDA: How CUDA Can Run on AMD & Intel GPUs

    27/08/2025

    The True Story of ZLUDA: How CUDA Can Run on AMD & Intel GPUs

    Listen to the story of ZLUDA directly from Andrzej Janik! From Intel beginnings to AMD, hear the untold story of running CUDA apps on non-Nvidia GPUs. Learn about the journey, challenges, and future of multi-vendor AI compute. #ZLUDA #AMD #CUDA 02:47 - What drew you into GPU software? 06:33 - Why start the ZLUDA project? 08:16 - When did you realize CUDA was viable? 09:56 - What happened at Intel? 11:45 - How did you transition to AMD? 14:58 - What are the challenges? 17:13 - Why did AMD stop funding? 19:59 - Where is ZLUDA today?" 🌐 Connect with us: https://www.linkedin.com/in/jtatarchuk https://github.com/vosen

    29 min
  4. Why the World Needs AMD for Sovereign AI with Keith Strier @ AMD

    27/08/2025

    Why the World Needs AMD for Sovereign AI with Keith Strier @ AMD

    Keith Strier explains the origins of sovereign AI, and why he moved from NVIDIA to AMD. He unpacks the GPU divide, silicon diversity, and why nations are now embracing open source and the ROCm ecosystem. 02:10 – Quitting 17-yr consulting for NVIDIA04:55 – NVIDIA culture shock: flat & fast07:32 – EY’s first AI practice (2016)10:08 – Estonia & Malta AI strategies12:56 – Launching NVIDIA’s “AI Nations”14:30 – ChatGPT hits; Jensen pivots17:05 – GPU land-grab by governments19:40 – Real bottleneck: data centers23:55 – Move to AMD to scale AI infra #BeyondCUDA #AIInfrastructure #AMD 🌐 Connect with us:https://www.linkedin.com/in/jtatarchukhttps://www.linkedin.com/in/keithstrier/

    43 min
  5. How Zyphra is Cutting AI Training Costs with AMD GPUs

    27/08/2025

    How Zyphra is Cutting AI Training Costs with AMD GPUs

    Quentin Anthony, model training lead at Zyphradiscussing building a multimodal agent system for enterprises. He covers optimizing models, hardware, and reducing training costs.  02:45 - Oak Ridge National Lab Work05:53 - How to make models personalizable offline?08:13 - How do hybrid models differ?09:38 - How to reduce training costs?11:56 - What is Quentin excited about?13:09 - What are the biggest challenges?16:14 - What's next for Zyphra? #TensorWave #AMDInstinct #AICloud 🌐 Connect with us:https://www.linkedin.com/in/jtatarchukhttps://www.linkedin.com/in/quentin-anthony

    27 min
  6. How dstack is Cutting GPU Cloud Costs 3–7x with Smarter Orchestration

    27/08/2025

    How dstack is Cutting GPU Cloud Costs 3–7x with Smarter Orchestration

    How we cuts cloud GPU costs 3-7x! Andrey Chepstov - CEO @ dstack (https://dstack.ai) chats with Jeff Tatarchuk on open source AI & redefining infrastructure. #AI #OpenSource #GPUs 00:29 - Intro and journey at JetBrains.  09:02 - How was dstack born?  13:14 - What are the challenges with Kubernetes?  18:36 - What problems does dstack solve?  26:21 - dstack roadmap and features.  30:25 - Open source journey and community building.  42:03 - What does Beyond CUDA mean?   🌐 Connect with us:https://www.linkedin.com/in/jtatarchuk/https://www.linkedin.com/in/andrey-cheptsov (00:00) - C2004 Andrey Cheptsov - Audio (00:24) - Guest Introduction: Andre Cheep (01:12) - Andre's Early Interest in Tech (02:52) - Journey at JetBrains (06:31) - Lessons from JetBrains (09:14) - The Birth of DST Stack (13:32) - Challenges with Kubernetes (18:49) - DST Stack's Solutions and Vision (24:12) - Challenges with Kubernetes and Market Dynamics (24:53) - The Importance of Kubernetes in Cloud Services (25:35) - Competing with Kubernetes: A New Approach (26:54) - DST Stack Roadmap and Exciting Features (27:20) - GPU Health Checks: A Game Changer (30:41) - Open Source Journey and Community Building (34:36) - Technical Challenges and Ecosystem Dynamics (36:00) - Cost Efficiency and Surprising Use Cases (39:50) - Future Plans and Community Involvement (42:48) - Final Thoughts and Beyond CUDA

    45 min
  7. Koosh Azimian on AI, Biotech, and the Future of Big Pharma

    27/08/2025

    Koosh Azimian on AI, Biotech, and the Future of Big Pharma

    Ex-Meta tech lead, on curing cancer with molecule programming! #AI #Biotech #GPUs 00:23 - What Sparked Kush's AI Journey?00:33 - How AI Models are Built00:43 - Can AI Cure Cancer?01:16 - What Does Beyond Cuda Mean?00:51 - What is Molecule Programming?00:13 - US vs China: Who's Ahead in AI?00:17 - What is AI Beyond LLMs?00:22 - How Did Kush Start His Company? 🌐 Connect with us:https://www.linkedin.com/in/jtatarchuk/https://www.linkedin.com/in/kooshiar/ (00:00) - C2003 Kooshiar Azimian - Audio (00:19) - Guest Introduction: Kush, Serial Entrepreneur (01:02) - Diving into AI Trends and ChatGPT-5 (01:45) - The Big Players in the AI Race (01:53) - Meta's Ad Ranking and AI Infrastructure (maybe add at the end?) (03:45) - Factors to Win the AI Race (04:59) - Product and Market Strategies in AI (06:28) - Trannstions back to AI (14:01) - US vs China in the AI Race (17:36) - Understanding AI Beyond LLMs (24:00) - Diving into AI and Protein Research (27:05) - AI's Role in Biotech and Health (29:41) - Challenges and Opportunities in Biotech (33:29) - Future of AI in Biotech and Cancer Research (44:13) - Bridging the Gap Between Tech and Pharma (51:28) - Conclusion and Final Thoughts

    57 min
  8. The AMD Advantage: Anush Elangovan on Building AI Software to Compete with CUDA

    27/08/2025

    The AMD Advantage: Anush Elangovan on Building AI Software to Compete with CUDA

    Beyond CUDA

    47 min
  9. No Kernels Needed for Speed with Jay Dawani @ Lumerian Labs

    19/08/2025

    No Kernels Needed for Speed with Jay Dawani @ Lumerian Labs

    Jay Dawani from Lemurian Labs talks about GPU performance and how they're uniting the stack for accessible AI development.  #AIdevelopment #BeyondCUDA #LemurianLabs 00:49 - Why Lemurian? 02:56 - Challenges in AI and Robotics. 06:13 - Reinventing Software for AI. 08:33 - Future of AI Hardware. 0:12:18 - Optimizing AI Performance. 0:16:38 - Prioritize to Make Things Easier? 0:22:23 - AI's Role in Software Development. 🌐 Connect with us: https://www.linkedin.com/in/jtatarchuk https://ca.linkedin.com/in/jaydawani (00:00) - C1777 Jay Dawani (00:47) - The Story Behind Lemurian Labs (06:11) - Reinventing Software for AI (08:29) - The Future of AI Hardware and Software Integration (12:16) - Optimizing AI Performance (15:59) - The Path Forward in AI Development (19:37) - FPGA Frustrations and Alternatives (20:04) - The Future of Heterogeneous Computing (22:18) - AI's Role in Software Development (23:11) - Current Projects and Breakthroughs (27:21) - Partnerships and Collaborations (28:10) - Developer Engagement and Ecosystem (36:49) - Concluding Thoughts and Vision

    38 min
  10. AI's Next Chapter: AMD's Big Opportunity with Gregory Diamos @ ScalarLM

    22/07/2025

    AI's Next Chapter: AMD's Big Opportunity with Gregory Diamos @ ScalarLM

    History of CUDA with Greg Diamos, an early pioneer talk about CUDA's challenges, successes, and its impact on AI. Is the CUDA moat shrinking? 00:00 - Origins of CUDA 02:15 - Greg's Early Interest 03:30 - Joining Nvidia 04:45 - Build a Faster Computer 06:30 - CUDA Dominated AI Research 08:50 - What is Nvidia's Moat? 13:45 - AMD's Accelerators 17:35 - More People Using AMD #CUDA #AMD #AI 🌐 Connect with us: https://www.linkedin.com/in/jtatarchuk https://www.linkedin.com/in/gregory-diamos-1a8b9083/ (00:00) - [HIGHLIGHT CLIP] (01:03) - Greg's Early Interest in Electrical Engineering (02:10) - Joining Nvidia and the Early Days of CUDA (04:52) - Challenges and Successes of CUDA (07:09) - The CUDA Moat and Its Implications (11:41) - AMD's Role and Potential in AI (18:38) - Introducing Scaler LM (29:01) - Future of AI and Beyond CUDA (32:05) - Conclusion and How to Get Involved

    33 min
  • 10 episodios

Acerca de

Beyond CUDA is where the future of AI infrastructure gets real. Hosted by Jeff Tatarchuk, co-founder of TensorWave, the show dives deep with the founders, developers, and investors redefining how AI is built and scaled. From bleeding-edge models to open-source breakthroughs, Jeff unpacks the tech, tactics, and people shaping what’s next—beyond the NVIDIA-dominated status quo.

Información

  • Creador
    TensorWave
  • Años de actividad
    2 k
  • Episodios
    10
  • Clasificación
    Apto
  • Copyright
    © 2025 TensorWave, Inc.
  • Mostrar sitio web
    Beyond CUDA