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
Uncaught SIGSEGV (SEGV_1722) at 0x7ffd45a1cf19 #374
Comments
I used llamafile-0.6.2.exe to run the model with the same parameters and it was fine. |
Can you try llamafile-0.8.1 which was just released and tell me if it works? |
Operating Environment @jart It's the same mistake. ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no �[30;101merror�[0m: Uncaught SIGSEGV (SEGV_1722) at 0x7fff9228cf19 on DESKTOP-3QAL3JT pid 17548 tid 20232 RAX 0000000000000000 RBX 00000000000006ba RDI 00007fff7c2f3010 XMM0 00000000001c00000000000000000008 XMM8 00000000000000000000000000000000 cosmoaddr2line /D/ai/llamafile/llamafile-0.8.1.exe 7fff9228cf19 0000008f4620 7fff9228cf19 NULL+0 llamafile-0.8.1.exe -m Llama3-8B-Chinese-Chat-q8.gguf -ngl 0 |
llm_load_print_meta: PAD token = 128009 '<|eot_id|>'
llm_load_print_meta: LF token = 128 'Ä'
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
ggml_cuda_init: found 2 ROCm devices:
Device 0: AMD Radeon(TM) Graphics, compute capability 9.2, VMM: no
Device 1: AMD Radeon(TM) Graphics, compute capability 9.2, VMM: no
�[30;101merror�[0m: Uncaught SIGSEGV (SEGV_1722) at 0x7ffd45a1cf19 on DESKTOP-3QAL3JT pid 53596 tid 16724
llamafile-0.8.exe
No error information (win32 error 2)
Windows Cosmopolitan 3.3.3 MODE=x86_64 DESKTOP-3QAL3JT 0.0-0
RAX 0000000000000000 RBX 00000000000006ba RDI 00007ffd36753010
RCX 0000000000000000 RDX 0000000000000000 RSI 0000000000000000
RBP 0000000000000011 RSP 00007000007d6430 RIP 00007ffd45a1cf19
R8 0000000000000000 R9 0000000000000000 R10 0000000000000000
R11 0000000000000000 R12 000000000e3278e0 R13 00000000000006ba
R14 0000000000000000 R15 00007000007d66f0
TLS 000000000081de40
XMM0 00000000001b00000000000000000008 XMM8 00000000000000000000000000000000
XMM1 000000000000000000000000001b02b4 XMM9 00000000000000000000000000000000
XMM2 00000000001b0cc00000000000000050 XMM10 00000000000000000000000000000000
XMM3 00000000000000000000000000000032 XMM11 00000000000000000000000000000000
XMM4 00007ffd4813b86b0000000000000000 XMM12 00000000000000000000000000000000
XMM5 00000000000000060000000000a7032e XMM13 00000000000000000000000000000000
XMM6 2974736574616c282033562046554747 XMM14 00000000000000000000000000000000
XMM7 2d2d2d2d2d2d2d2d2d2d2d2d2d2d2d2d XMM15 00000000000000000000000000000000
cosmoaddr2line /D/ai/llamafile/llamafile-0.8.exe 7ffd45a1cf19
0000008f2620 7ffd45a1cf19 NULL+0
llamafile-0.8.exe -m Llama3-8B-Chinese-Chat-q8.gguf -ngl 0
Terminating on uncaught SIGSEGV. Pass --strace and/or ShowCrashReports() for details.
The text was updated successfully, but these errors were encountered: