Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Vulkan crashes #2559

Open
jech opened this issue Nov 14, 2024 · 0 comments
Open

Vulkan crashes #2559

jech opened this issue Nov 14, 2024 · 0 comments

Comments

@jech
Copy link

jech commented Nov 14, 2024

The vulkan build has started crashing on my machine. Reverting to 300c07b fixes the issue. A backtrace follows.

#0  __strlen_avx2 () at ../sysdeps/x86_64/multiarch/strlen-avx2.S:76
#1  0x00007ffff7987b60 in __printf_buffer (buf=buf@entry=0x7fffffffb570, 
    format=0x5555556e7dd8 "ggml_vulkan: %d = %s (%s) | uma: %d | fp16: %d | w size: %d\n", ap=0x7fffffffb718, mode_flags=mode_flags@entry=0)
    at ./stdio-common/vfprintf-process-arg.c:435
#2  0x00007ffff79aaeae in __vsnprintf_internal (
    string=0x7fffffffb650 "ggml_vulkan: 0 = Intel(R) UHD Graphics 620 (KBL GT(", maxlen=128, format=0x7fffffffb570 "P\266\377\377\377\177", 
    args=0x5555556e7dd8, mode_flags=0) at ./libio/vsnprintf.c:96
#3  ___vsnprintf (
    string=string@entry=0x7fffffffb650 "ggml_vulkan: 0 = Intel(R) UHD Graphic20 (KBL GT2) (", maxlen=maxlen@entry=128, 
    format=format@entry=0x5555556e7dd8 "ggml_vulkan: %d = %s (%s) | uma: %d |16: %d | warp size: %d\n", args=args@entry=0x7fffffffb718)
    at ./libio/vsnprintf.c:103
#4  0x00005555555e8a0f in ggml_log_internal_v (level=GGML_LOG_LEVEL_DEBUG, 
    format=0x5555556e7dd8 "ggml_vulkan: %d = %s (%s) | uma: %d | fp16: %d | w size: %d\n", args=args@entry=0x7fffffffb718) at ggml/src/ggml.c:334
#5  0x00005555555edd3f in ggml_log_internal (level=<optimized out>, 
    format=<optimized out>) at ggml/src/ggml.c:350
#6  0x00005555555af53c in ggml_vk_print_gpu_info (idx=idx@entry=0)
    at /usr/include/c++/14/bits/basic_string.h:227
#7  0x00005555555b10e8 in ggml_vk_instance_init ()
--Type <RET> for more, q to quit, c to continue without paging--c
    at ggml/src/ggml-vulkan.cpp:2229
#8  0x00005555555b1ca9 in ggml_vk_get_device_count ()
    at ggml/src/ggml-vulkan.cpp:6167
#9  ggml_backend_vk_get_device_count () at ggml/src/ggml-vulkan.cpp:6631
#10 0x00005555555b1cc9 in ggml_backend_vk_reg_get_device_count (
    reg=<optimized out>) at ggml/src/ggml-vulkan.cpp:6878
#11 0x0000555555636009 in ggml_backend_registry::register_backend (
    this=0x5555559847c0 <get_reg()::reg>, reg=<optimized out>)
    at ggml/src/ggml-backend.cpp:609
#12 ggml_backend_registry::ggml_backend_registry (
    this=0x5555559847c0 <get_reg()::reg>) at ggml/src/ggml-backend.cpp:583
#13 get_reg () at ggml/src/ggml-backend.cpp:623
#14 0x0000555555636139 in ggml_backend_reg_count ()
    at ggml/src/ggml-backend.cpp:638
#15 0x000055555568be0e in whisper_init_with_params_no_state (
    loader=loader@entry=0x7fffffffdb40, params=...) at src/whisper.cpp:3671
#16 0x000055555568c378 in whisper_init_from_file_with_params_no_state (
    path_model=0x55555599bec0 "models/ggml-base.en.bin", params=...)
    at src/whisper.cpp:3611
#17 0x000055555568fabd in whisper_init_from_file_with_params (
    path_model=<optimized out>, 
    params=<error reading variable: Cannot access memory at address 0x0>)
    at src/whisper.cpp:3689
#18 0x00005555556e154c in whisper_bench_full (params=...)
    at /usr/include/c++/14/bits/basic_string.h:227
#19 0x000055555558f409 in main (argc=1, argv=0x7fffffffe8c8)
    at examples/bench/bench.cpp:168
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant