Files
amd-strix-halo-toolboxes/benchmark/results/gemma-3-27b-it-BF16-00001-of-00002__vulkan_amdvlk__fa1__longctx32768.log
T
Donato Capitella a7ace8dba7 updted benchmarks
2026-03-30 08:37:15 +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(+0x3c25) [0x7f5b5347fc25]
/lib64/libggml-base.so.0(ggml_print_backtrace+0x1eb) [0x7f5b5347ffeb]
/lib64/libggml-base.so.0(+0x16669) [0x7f5b53492669]
/lib64/libstdc++.so.6(+0x1ebfc) [0x7f5b52bf6bfc]
/lib64/libstdc++.so.6(_ZSt10unexpectedv+0x0) [0x7f5b52be0d3a]
/lib64/libstdc++.so.6(+0x1eea8) [0x7f5b52bf6ea8]
/lib64/libggml-vulkan.so.0(+0x16b68) [0x7f5b5353cb68]
/lib64/libggml-vulkan.so.0(+0xfcfd0) [0x7f5b53622fd0]
/lib64/libggml-base.so.0(ggml_backend_sched_graph_compute_async+0x3b2) [0x7f5b5349b092]
/lib64/libllama.so.0(_ZN13llama_context13graph_computeEP11ggml_cgraphb+0xa0) [0x7f5b56db0e70]
/lib64/libllama.so.0(_ZN13llama_context14process_ubatchERK12llama_ubatch14llm_graph_typeP22llama_memory_context_iR11ggml_status+0xe5) [0x7f5b56db3445]
/lib64/libllama.so.0(_ZN13llama_context6decodeERK11llama_batch+0x35f) [0x7f5b56db9aaf]
/lib64/libllama.so.0(llama_decode+0xe) [0x7f5b56dbb42e]
/usr/sbin/llama-bench() [0x41cc3b]
/usr/sbin/llama-bench() [0x41977f]
/lib64/libc.so.6(+0x35b5) [0x7f5b528c75b5]
/lib64/libc.so.6(__libc_start_main+0x88) [0x7f5b528c7668]
/usr/sbin/llama-bench() [0x41b595]
terminate called after throwing an instance of 'vk::DeviceLostError'
what(): vk::Queue::submit: ErrorDeviceLost
✖ ! [vulkan_amdvlk] gemma-3-27b-it-BF16-00001-of-00002__fa1 __longctx32768 failed (exit 0)