llama.cpp b7083 Vulkan: Llama-3.1-Tulu-3-8B-Q8_0 prefill 1024 tok on amd-radeon-rx-9070

Phoronix Test Suite run of llama.cpp b7083 with the Vulkan backend, one shared host (Michael Larabel, 2025-12-08, result 2512070-NE-LLAMACPPV90). Intel Arc B580 on Mesa 26.0-dev ANV, AMD Radeon cards on Mesa 26.0-dev RADV, both under Linux 6.18. Geometric mean of N=3 runs. ONE request: the prompt-processing test prefills a single prompt and the text-generation test decodes a single 128-token completion. NOT an aggregate across concurrent requests. Batch size is the Phoronix llama.cpp default of 1 for these two tests. Quantization is Q8_0 as named in the result title. Power, clocks and thermals were not published. Card: amd-radeon-rx-9070. Model: Llama-3.1-Tulu-3-8B-Q8_0. PREFILL of one request, prompt-processing-1024 test, not aggregate.

Geometric mean, N=3, read from the published result SVG llamacpp-vulkan-tulu3-8b-pp1. The same run also published pp512 and pp2048 for some models; pp1024 is the cell filed so the four models stay comparable.