Eval bug: qwen2-vl-2B on jetson agx orin ; try to allocate 655521.35 MB memory

[chaoszzz123]

Name and Version

llama.cpp-master

Operating systems

Linux

GGML backends

CUDA

Hardware

jetson agx orin 64 GB

Models

qwen2-vl-2B

Problem description & steps to reproduce

ggml_aligned_malloc: insufficient memory (attempted to allocate 655521.35 MB)
ggml_backend_cpu_buffer_type_alloc_buffer: failed to allocate buffer of size 687363958272
ggml_gallocr_reserve_n: failed to allocate CPU buffer of size 687363958272
/home/lab123/llama.cpp-master/ggml/src/ggml-backend.cpp:262: GGML_ASSERT(buf != NULL && "tensor buffer not set") failed
Could not attach to process. If your uid matches the uid of the target
process, check the setting of /proc/sys/kernel/yama/ptrace_scope, or try
again as the root user. For more details, see /etc/sysctl.d/10-ptrace.conf
ptrace: Operation not permitted.
No stack.
The program is not being run.
Aborted (core dumped)

First Bad Commit

No response

Relevant log output

ggml_aligned_malloc: insufficient memory (attempted to allocate 655521.35 MB)
ggml_backend_cpu_buffer_type_alloc_buffer: failed to allocate buffer of size 687363958272
ggml_gallocr_reserve_n: failed to allocate CPU buffer of size 687363958272
/home/lab123/llama.cpp-master/ggml/src/ggml-backend.cpp:262: GGML_ASSERT(buf != NULL && "tensor buffer not set") failed
Could not attach to process.  If your uid matches the uid of the target
process, check the setting of /proc/sys/kernel/yama/ptrace_scope, or try
again as the root user.  For more details, see /etc/sysctl.d/10-ptrace.conf
ptrace: Operation not permitted.
No stack.
The program is not being run.
Aborted (core dumped)