Tenstorrent

LG confirmed in November 2024 that its Tenstorrent chiplet collaboration expanded to development of SoCs and systems for LG product applications, adding a named industrial design partner beyond supercluster announcements.

Tenstorrent is deploying Galaxy superclusters and heterogeneous AI systems in Japan and other markets, with customer and sovereign AI infrastructure expanding beyond evaluation-stage use.

Tenstorrent is deploying Galaxy superclusters and heterogeneous AI systems in Japan and other markets, with customer and sovereign AI infrastructure expanding beyond evaluation-stage use.

Tenstorrent documentation shows a vertically integrated AI compute stack spanning Tensix and RISC-V architectures, accelerator cards and servers, TT-Forge/TT-MLIR compilers, TT-NN and TT-Metalium software, cloud-native support and production inference tooling.

Tenstorrent develops open AI accelerators, Networked AI architecture, RISC-V CPU IP, compiler/software systems and Galaxy-scale infrastructure designed as an alternative to GPU-centric architectures.

Tenstorrent develops open AI accelerators, Networked AI architecture, RISC-V CPU IP, compiler/software systems and Galaxy-scale infrastructure designed as an alternative to GPU-centric architectures.

Tenstorrent has expanded internationally, built strategic deployment partnerships and continues to scale hardware, systems and software under experienced semiconductor leadership.

Tenstorrent has expanded internationally, built strategic deployment partnerships and continues to scale hardware, systems and software under experienced semiconductor leadership.

Tenstorrent closed more than $693M in Series D funding at a $2B pre-money valuation, with strategic and institutional investors including Samsung, Hyundai, Fidelity, Baillie Gifford, LG Technology Ventures and Export Development Canada, supporting continued global hardware, software and systems expansion.

Tenstorrent engineering spans RISC-V CPUs, Tensor AI processors, open-source software, AI compilers, low-level kernels, scale-out systems, firmware, silicon validation, high-speed I/O and infrastructure, demonstrating unusually broad portability across semiconductor and AI systems roles.

Accelerator architecture, RISC-V, compilers, distributed inference and AI systems skills transfer exceptionally broadly across semiconductor and AI infrastructure employers.

Accelerator architecture, RISC-V, compilers, distributed inference and AI systems skills transfer exceptionally broadly across semiconductor and AI infrastructure employers.