--- title: Springing into AI: PyTorch Conference Europe & ICLR 2026 description: Collabora is presenting at two AI conferences in April: PyTorch Conference Europe in Paris (April 7-8) and ICLR in Rio de Janeiro (April 23-27). At PyTorch... canonical: https://daily.dev/posts/springing-into-ai-pytorch-conference-europe-iclr-2026-7njspplxl twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Springing into AI: PyTorch Conference Europe & ICLR 2026 | daily.dev og:description: Collabora is presenting at two AI conferences in April: PyTorch Conference Europe in Paris (April 7-8) and ICLR in Rio de Janeiro (April 23-27). At PyTorch... og:url: https://daily.dev/posts/springing-into-ai-pytorch-conference-europe-iclr-2026-7njspplxl og:image: https://api.daily.dev/og/posts/7NjSPpLxL.png og:image:alt: Springing into AI: PyTorch Conference Europe & ICLR 2026 og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Springing into AI: PyTorch Conference Europe & ICLR 2026 **[Collabora Blog](https://daily.dev/sources/collabora)** · 2 min read · 0 upvotes · 0 comments ## Summary Collabora is presenting at two AI conferences in April: PyTorch Conference Europe in Paris (April 7-8) and ICLR in Rio de Janeiro (April 23-27). At PyTorch Conference Europe, Marcus Edel and Vineet Suryan will present a poster on 'Bringing BitNet to ExecuTorch via Vulkan', which enables ternary-weight (1.58-bit) LLM inference on mobile GPUs using Vulkan compute shaders, reducing model size and memory bandwidth for edge devices. Italo Nicola will attend ICLR to explore the latest AI developments. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What does 'Bringing BitNet to ExecuTorch via Vulkan' enable for edge LLM inference? It enables ternary-weight (1.58-bit), low-bit LLM inference within ExecuTorch's standard export and runtime, targeting mobile GPU execution on Vulkan-capable devices. By combining BitNet's compact packed operators with Vulkan compute shaders, the implementation reduces model size and memory bandwidth while improving on-device inference performance for edge LLM models. _Engineers optimizing LLM inference for edge devices track work like this on daily.dev._ ## Similar posts on daily.dev - [PyTorch Conference Europe 2026: A Landmark Moment for Open Source AI in Paris – PyTorch](https://daily.dev/posts/pytorch-conference-europe-2026-a-landmark-moment-for-open-source-ai-in-paris-pytorch-zpgtevbg5) · PyTorch · 2 upvotes · 0 comments - [PyTorchCon Europe Schedule is Live – PyTorch](https://daily.dev/posts/pytorchcon-europe-schedule-is-live-pytorch-ruvqxtrey) · PyTorch · 0 upvotes · 0 comments - [KubeCon \+ CloudNativeCon, OpenInfra Summit and PyTorch Conference Unite in China to Scale AI](https://daily.dev/posts/kubecon-cloudnativecon-openinfra-summit-and-pytorch-conference-unite-in-china-to-scale-ai-kv38kbjul) · CNCF · 0 upvotes · 0 comments - [Machine Learning Blog \| ML@CMU \| Carnegie Mellon University](https://daily.dev/posts/machine-learning-blog-ml-cmu-carnegie-mellon-university-ynzk2dhmg) · ML CMU · 2 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#pytorch](https://daily.dev/tags/pytorch), [#vulkan](https://daily.dev/tags/vulkan) [View this post on daily.dev](https://daily.dev/posts/springing-into-ai-pytorch-conference-europe-iclr-2026-7njspplxl) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Springing into AI: PyTorch Conference Europe & ICLR 2026","url":"https://daily.dev/posts/springing-into-ai-pytorch-conference-europe-iclr-2026-7njspplxl","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/springing-into-ai-pytorch-conference-europe-iclr-2026-7njspplxl"},"datePublished":"2026-08-11T08:57:24.724Z","dateModified":"2026-08-11T09:41:11.425Z","description":"Collabora is presenting at two AI conferences in April: PyTorch Conference Europe in Paris (April 7-8) and ICLR in Rio de Janeiro (April 23-27). At PyTorch...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/67bd1538994925511b29b95c218fd848?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/67bd1538994925511b29b95c218fd848?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Collabora Blog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collabora Blog","logo":"https://media.daily.dev/image/upload/s--ZGZ0FjqS--/f_auto,q_auto/v1786438306/logos/collabora?_a=BAMAMicg0","url":"https://daily.dev/sources/collabora"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/springing-into-ai-pytorch-conference-europe-iclr-2026-7njspplxl","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,pytorch,vulkan","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collabora Blog","item":"https://daily.dev/sources/collabora"},{"@type":"ListItem","position":3,"name":"Springing into AI: PyTorch Conference Europe & ICLR 2026"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/springing-into-ai-pytorch-conference-europe-iclr-2026-7njspplxl#faq","mainEntity":[{"@type":"Question","name":"What does 'Bringing BitNet to ExecuTorch via Vulkan' enable for edge LLM inference?","acceptedAnswer":{"@type":"Answer","text":"It enables ternary-weight (1.58-bit), low-bit LLM inference within ExecuTorch's standard export and runtime, targeting mobile GPU execution on Vulkan-capable devices. By combining BitNet's compact packed operators with Vulkan compute shaders, the implementation reduces model size and memory bandwidth while improving on-device inference performance for edge LLM models. Engineers optimizing LLM inference for edge devices track work like this on daily.dev."}}]} ```