AMD releases GAIA 0.25 with improvements for local AI agents on Ryzen AI
AMD Ryzen AI Developer Platform OS updated with ROCm 10.0, Linux 7.2
AMD Ryzen AI Developer Platform OS updated with ROCm 10.0, Linux 7.2
Phoronix reports AMD Linux 7.4 drivers boost Radeon iGPU AI/LLM performance up to 18-23%
Phoronix reports AMD Linux 7.4 drivers boost Radeon iGPU AI/LLM performance up to 18-23%
AMD released ROCm 10.0, a major version of its open GPU compute stack, framed around agentic AI workloads. The jump from 7.14 to 10.0 came just a month after the previous release, and llama.cpp support is pending via an open pull request.
AMD released ROCm 10.0, a major version of its open GPU compute stack, framed around agentic AI workloads. The jump from 7.14 to 10.0 came just a month after the previous release, and llama.cpp support is pending via an open pull request.
A user created a custom quantized version of Qwen 3.5 122B called 'Heretic ROCmFP4 iMatrix' running on AMD Strix Halo hardware. The model achieves 28.45 tok/s with 10B active parameters and 60.70 GiB memory usage, demonstrating efficient inference on consumer hardware.
A user created a custom quantized version of Qwen 3.5 122B called 'Heretic ROCmFP4 iMatrix' running on AMD Strix Halo hardware. The model achieves 28.45 tok/s with 10B active parameters and 60.70 GiB memory usage, demonstrating efficient inference on consumer hardware.
AMD has tagged a tech preview of ROCm 7.14, codenamed 'TheRock', for its latest GPU compute stack. The preview is available for testing and includes support for newer AMD GPUs. This release aims to improve performance and compatibility for AI and HPC workloads on AMD hardware.
AMD has tagged a tech preview of ROCm 7.14, codenamed 'TheRock', for its latest GPU compute stack. The preview is available for testing and includes support for newer AMD GPUs. This release aims to improve performance and compatibility for AI and HPC workloads on AMD hardware.