Files
amd-strix-halo-toolboxes/benchmark/results/gemma-4-31B-it-UD-Q8_K_XL__vulkan_amdvlk__fa1__longctx32768.log
T
Donato Capitella 7aa6e6dea9 update benchmarks
2026-04-11 11:18:45 +01:00

24 lines
1.5 KiB
Plaintext

ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Radeon 8060S Graphics (AMD open-source driver) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
/lib64/libggml-base.so.0(+0x4465) [0x7f8de9476465]
/lib64/libggml-base.so.0(ggml_print_backtrace+0x1eb) [0x7f8de947682b]
/lib64/libggml-base.so.0(+0x16ed9) [0x7f8de9488ed9]
/lib64/libstdc++.so.6(+0x1ebfc) [0x7f8de8becbfc]
/lib64/libstdc++.so.6(_ZSt10unexpectedv+0x0) [0x7f8de8bd6d3a]
/lib64/libstdc++.so.6(+0x1eea8) [0x7f8de8becea8]
/lib64/libggml-vulkan.so.0(+0x173b2) [0x7f8de95463b2]
/lib64/libggml-vulkan.so.0(+0x1075d0) [0x7f8de96365d0]
/lib64/libggml-base.so.0(ggml_backend_sched_graph_compute_async+0x3b2) [0x7f8de9492112]
/lib64/libllama.so.0(_ZN13llama_context13graph_computeEP11ggml_cgraphb+0xa0) [0x7f8ded0ad530]
/lib64/libllama.so.0(_ZN13llama_context14process_ubatchERK12llama_ubatch14llm_graph_typeP22llama_memory_context_iR11ggml_status+0xe5) [0x7f8ded0afb05]
/lib64/libllama.so.0(_ZN13llama_context6decodeERK11llama_batch+0x35f) [0x7f8ded0b626f]
/lib64/libllama.so.0(llama_decode+0xe) [0x7f8ded0b7bee]
/usr/sbin/llama-bench() [0x41a1bb]
/usr/sbin/llama-bench() [0x416ec6]
/lib64/libc.so.6(+0x35b5) [0x7f8de88bd5b5]
/lib64/libc.so.6(__libc_start_main+0x88) [0x7f8de88bd668]
/usr/sbin/llama-bench() [0x4189d5]
terminate called after throwing an instance of 'vk::DeviceLostError'
what(): vk::Queue::submit: ErrorDeviceLost
✖ ! [vulkan_amdvlk] gemma-4-31B-it-UD-Q8_K_XL__fa1 __longctx32768 failed (exit 0)