@Modular: The graph compiler, runtime and hardware backends join the kernels, models, serving infrastructure, and Mojo compiler +…
Summary
Modular announced that its graph compiler, runtime, and hardware backends are now open-sourced alongside kernels, models, serving infrastructure, and the Mojo compiler and standard library, letting developers build and deploy AI across hardware platforms without vendor lock-in.
Similar Articles
@Modular: We're the #1 trending repo on @github today. The Mojo compiler went open source at ModCon this week, and developers not…
Modular announces that the Mojo compiler has gone open source, the platform now supports six hardware architectures including NVIDIA, AMD, and new ASICs, and Modular Cloud is officially launched.
@dMatrix_AI: #ModCon2026 highlighted the momentum behind heterogeneous computing and open AI infrastructure. With @Qualcomm, d-Matri…
At ModCon 2026, Modular announced that Mojo 1.0 is fully open source under Apache 2.0, Modular Cloud is publicly available, and the platform now supports various AI accelerators including AWS Trainium, Google TPUs, and Qualcomm hardware.
@Modular: Today's AI software is fragmented. Every accelerator has its own compiler, kernel libraries, runtime, and development p…
Modular presents a unified compute layer to address AI software fragmentation, demonstrating faster hardware enablement through collaborations with HTEC and d-Matrix to extend MAX and Mojo to new accelerators like Google TPU.
The Mojo language (by Modular, now Qualcomm) is now open-source
Mojo 1.0 has been fully open-sourced under an Apache 2.0 license, making the AI programming language accessible to developers worldwide. The announcement also includes the launch of Modular Cloud and expanded support for various hardware accelerators.
Mojo: Modular’s unified device accelerator language
Mojo 是 Modular 推出的统一设备加速器语言，其开源栈中的其余组件（图编译器、MLRT）近期已在 GitHub 上开放。