home.social

#executorch — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #executorch, aggregated by home.social.

  1. BitNet-style ternary quantization is helping bring smaller, more bandwidth-efficient LLMs to ExecuTorch through its Vulkan backend, with portable GPU execution for edge devices where performance and memory matter.

    Explore the technical details presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  2. BitNet-style ternary quantization is helping bring smaller, more bandwidth-efficient LLMs to ExecuTorch through its Vulkan backend, with portable GPU execution for edge devices where performance and memory matter.

    Explore the technical details presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  3. BitNet-style ternary quantization is helping bring smaller, more bandwidth-efficient LLMs to ExecuTorch through its Vulkan backend, with portable GPU execution for edge devices where performance and memory matter.

    Explore the technical details presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  4. BitNet-style ternary quantization is helping bring smaller, more bandwidth-efficient LLMs to ExecuTorch through its Vulkan backend, with portable GPU execution for edge devices where performance and memory matter.

    Explore the technical details presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  5. BitNet-style ternary quantization is helping bring smaller, more bandwidth-efficient LLMs to ExecuTorch through its Vulkan backend, with portable GPU execution for edge devices where performance and memory matter.

    Explore the technical details presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  6. Smaller models. Lower bandwidth. Portable GPU execution.

    How BitNet-style ternary quantization is helping bring efficient LLM inference to ExecuTorch through its Vulkan backend, targeting edge devices where performance and memory matter.

    Recap our work from PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  7. Smaller models. Lower bandwidth. Portable GPU execution.

    How BitNet-style ternary quantization is helping bring efficient LLM inference to ExecuTorch through its Vulkan backend, targeting edge devices where performance and memory matter.

    Recap our work from PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  8. Smaller models. Lower bandwidth. Portable GPU execution.

    How BitNet-style ternary quantization is helping bring efficient LLM inference to ExecuTorch through its Vulkan backend, targeting edge devices where performance and memory matter.

    Recap our work from PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  9. Smaller models. Lower bandwidth. Portable GPU execution.

    How BitNet-style ternary quantization is helping bring efficient LLM inference to ExecuTorch through its Vulkan backend, targeting edge devices where performance and memory matter.

    Recap our work from PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  10. Smaller models. Lower bandwidth. Portable GPU execution.

    How BitNet-style ternary quantization is helping bring efficient LLM inference to ExecuTorch through its Vulkan backend, targeting edge devices where performance and memory matter.

    Recap our work from PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  11. BitNet-style ternary brings LLM inference to ExecuTorch via its Vulkan backend, enabling much smaller, bandwidth-efficient models with portable GPU execution on edge devices.

    Learn more about this work presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    @pytorch #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  12. BitNet-style ternary brings LLM inference to ExecuTorch via its Vulkan backend, enabling much smaller, bandwidth-efficient models with portable GPU execution on edge devices.

    Learn more about this work presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    @pytorch #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  13. BitNet-style ternary brings LLM inference to ExecuTorch via its Vulkan backend, enabling much smaller, bandwidth-efficient models with portable GPU execution on edge devices.

    Learn more about this work presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    @pytorch #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  14. BitNet-style ternary brings LLM inference to ExecuTorch via its Vulkan backend, enabling much smaller, bandwidth-efficient models with portable GPU execution on edge devices.

    Learn more about this work presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    @pytorch #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  15. BitNet-style ternary brings LLM inference to ExecuTorch via its Vulkan backend, enabling much smaller, bandwidth-efficient models with portable GPU execution on edge devices.

    Learn more about this work presented at PyTorch Conference Europe 2026: collabora.com/news-and-blog/bl

    @pytorch #PyTorch #PyCon #ExecuTorch #Vulkan #OpenSource

  16. Modern #Androids pack 45+ #TOPS of #NPU compute. Instead of draining battery, a native app using #ExecuTorch and #NNAPI runs 4-bit quantized #LLMs natively, turning smartphones into a massive, parallelized compute swarm. 🧠🔋 #EdgeAI #MachineLearning #AndroidDev

    Turning Android Phones Into An...

  17. Modern #Androids pack 45+ #TOPS of #NPU compute. Instead of draining battery, a native app using #ExecuTorch and #NNAPI runs 4-bit quantized #LLMs natively, turning smartphones into a massive, parallelized compute swarm. 🧠🔋 #EdgeAI #MachineLearning #AndroidDev

    Turning Android Phones Into An...

  18. Introducing Executorch: the revolutionary breakthrough that lets your #toaster run #PyTorch 🤖🔥, because who wouldn’t want #AI on their bread? 🍞 Meanwhile, developers everywhere are thrilled about "embedding" AI into devices that definitely needed it, like that smart fridge that judges your leftovers. 🍕🚫
    github.com/pytorch/executorch #Executorch #SmartDevices #FoodTech #HackerNews #ngated

  19. Introducing Executorch: the revolutionary breakthrough that lets your #toaster run #PyTorch 🤖🔥, because who wouldn’t want #AI on their bread? 🍞 Meanwhile, developers everywhere are thrilled about "embedding" AI into devices that definitely needed it, like that smart fridge that judges your leftovers. 🍕🚫
    github.com/pytorch/executorch #Executorch #SmartDevices #FoodTech #HackerNews #ngated

  20. Introducing Executorch: the revolutionary breakthrough that lets your #toaster run #PyTorch 🤖🔥, because who wouldn’t want #AI on their bread? 🍞 Meanwhile, developers everywhere are thrilled about "embedding" AI into devices that definitely needed it, like that smart fridge that judges your leftovers. 🍕🚫
    github.com/pytorch/executorch #Executorch #SmartDevices #FoodTech #HackerNews #ngated

  21. Introducing Executorch: the revolutionary breakthrough that lets your #toaster run #PyTorch 🤖🔥, because who wouldn’t want #AI on their bread? 🍞 Meanwhile, developers everywhere are thrilled about "embedding" AI into devices that definitely needed it, like that smart fridge that judges your leftovers. 🍕🚫
    github.com/pytorch/executorch #Executorch #SmartDevices #FoodTech #HackerNews #ngated