Name and Version
Binary release 'prism-b10709-9a9394a'
Operating systems
Linux
GGML backends
CUDA
Hardware
System Info:
- Asus A14 / RTX 4060
- Ubuntu 24.04 by WSL
$ cat /etc/os-release
PRETTY_NAME="Ubuntu 24.04.5 LTS"
NAME="Ubuntu"
VERSION_ID="24.04"
VERSION="24.04.5 LTS (Noble Numbat)"
VERSION_CODENAME=noble
ID=ubuntu
ID_LIKE=debian
HOME_URL="https://www.ubuntu.com/"
SUPPORT_URL="https://help.ubuntu.com/"
BUG_REPORT_URL="https://bugs.launchpad.net/ubuntu/"
PRIVACY_POLICY_URL="https://www.ubuntu.com/legal/terms-and-policies/privacy-policy"
UBUNTU_CODENAME=noble
LOGO=ubuntu-logo
Models
No response
Problem description & steps to reproduce
I used releases 'prism-b10709-9a9394a' and run with CUDA 12.9, CUDA 13.3 & 13.4.
When i run "Linux x64 (CUDA 13.3)" binary with CUDA 13.[3,4], that have segemation fault like below:
But "Linux x64 (CUDA 12.8)" of release '9a9394a' works fine with CUDA 12 & CUDA 13
thans for your efforts.
First Bad Commit
No response
Relevant log output
Logs
$ dmesg -T | grep -i segfault
[Sun Sep 20 06:48:25 2026] llama-server[4344]: segfault at 1 ip 00007d9853846ff9 sp 00007ffc83ee01b0 error 6 in libnvidia-ptxjitcompiler.so.580.178.04[246ff9,7d985383f000+18e5000] likely on CPU 12 (core 6, socket 0)
[Sun Sep 20 06:48:46 2026] llama-server[4360]: segfault at 1 ip 00007c4aef246ff9 sp 00007fffdc2d92d0 error 6 in libnvidia-ptxjitcompiler.so.580.178.04[246ff9,7c4aef23f000+18e5000] likely on CPU 8 (core 4, socket 0)
Name and Version
Binary release 'prism-b10709-9a9394a'
Operating systems
Linux
GGML backends
CUDA
Hardware
System Info:
Models
No response
Problem description & steps to reproduce
I used releases 'prism-b10709-9a9394a' and run with CUDA 12.9, CUDA 13.3 & 13.4.
When i run "Linux x64 (CUDA 13.3)" binary with CUDA 13.[3,4], that have segemation fault like below:
But "Linux x64 (CUDA 12.8)" of release '9a9394a' works fine with CUDA 12 & CUDA 13
thans for your efforts.
First Bad Commit
No response
Relevant log output
Logs