Cannot use pre-built linux cpu wheel

[Bing-su]

Prerequisites

Please answer the following questions for yourself before submitting an issue.

• I am running the latest code. Development is very rapid so there are no tagged versions as of now.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new bug or useful enhancement to share.

Expected Behavior

The pre-built wheel is working properly.

Current Behavior

from llama_cpp import Llama

---------------------------------------------------------------------------
OSError                                   Traceback (most recent call last)
[/usr/local/lib/python3.12/dist-packages/llama_cpp/_ctypes_extensions.py](https://localhost:8080/#) in load_shared_library(lib_base_name, base_path)
     66             try:
---> 67                 return ctypes.CDLL(str(lib_path), **cdll_args)  # type: ignore
     68             except Exception as e:

4 frames
OSError: libc.musl-x86_64.so.1: cannot open shared object file: No such file or directory

During handling of the above exception, another exception occurred:

RuntimeError                              Traceback (most recent call last)
[/usr/local/lib/python3.12/dist-packages/llama_cpp/_ctypes_extensions.py](https://localhost:8080/#) in load_shared_library(lib_base_name, base_path)
     67                 return ctypes.CDLL(str(lib_path), **cdll_args)  # type: ignore
     68             except Exception as e:
---> 69                 raise RuntimeError(f"Failed to load shared library '{lib_path}': {e}")
     70 
     71     raise FileNotFoundError(

RuntimeError: Failed to load shared library '/usr/local/lib/python3.12/dist-packages/llama_cpp/lib/libllama.so': libc.musl-x86_64.so.1: cannot open shared object file: No such file or directory

Environment and Context

• Physical (or virtual) hardware you are using, e.g. for Linux:

Google Colab

$ lscpu

Architecture:                x86_64
  CPU op-mode(s):            32-bit, 64-bit
  Address sizes:             46 bits physical, 48 bit
                             s virtual
  Byte Order:                Little Endian
CPU(s):                      2
  On-line CPU(s) list:       0,1
Vendor ID:                   GenuineIntel
  Model name:                Intel(R) Xeon(R) CPU @ 2
                             .20GHz
    CPU family:              6
    Model:                   79
    Thread(s) per core:      2
    Core(s) per socket:      1
    Socket(s):               1
    Stepping:                0
    BogoMIPS:                4400.31
    Flags:                   fpu vme de pse tsc msr p
                             ae mce cx8 apic sep mtrr
                              pge mca cmov pat pse36 
                             clflush mmx fxsr sse sse
                             2 ss ht syscall nx pdpe1
                             gb rdtscp lm constant_ts
                             c rep_good nopl xtopolog
                             y nonstop_tsc cpuid tsc_
                             known_freq pni pclmulqdq
                              ssse3 fma cx16 pcid sse
                             4_1 sse4_2 x2apic movbe 
                             popcnt aes xsave avx f16
                             c rdrand hypervisor lahf
                             _lm abm 3dnowprefetch ss
                             bd ibrs ibpb stibp fsgsb
                             ase tsc_adjust bmi1 hle 
                             avx2 smep bmi2 erms invp
                             cid rtm rdseed adx smap 
                             xsaveopt arat md_clear a
                             rch_capabilities
Virtualization features:     
Virtualization features:     
  Hypervisor vendor:         KVM
  Virtualization type:       full
Caches (sum of all):         
  L1d:                       32 KiB (1 instance)
  L1i:                       32 KiB (1 instance)
  L2:                        256 KiB (1 instance)
  L3:                        55 MiB (1 instance)
NUMA:                        
  NUMA node(s):              1
  NUMA node0 CPU(s):         0,1
Vulnerabilities:             
  Gather data sampling:      Not affected
  Indirect target selection: Vulnerable
  Itlb multihit:             Not affected
  L1tf:                      Mitigation; PTE Inversio
                             n
  Mds:                       Vulnerable; SMT Host sta
                             te unknown
  Meltdown:                  Vulnerable
  Mmio stale data:           Vulnerable
  Reg file data sampling:    Not affected
  Retbleed:                  Vulnerable
  Spec rstack overflow:      Not affected
  Spec store bypass:         Vulnerable
  Spectre v1:                Vulnerable: __user point
                             er sanitization and user
                             copy barriers only; no s
                             wapgs barriers
  Spectre v2:                Vulnerable; IBPB: disabl
                             ed; STIBP: disabled; PBR
                             SB-eIBRS: Not affected; 
                             BHI: Vulnerable
  Srbds:                     Not affected
  Tsa:                       Not affected
  Tsx async abort:           Vulnerable
  Vmscape:                   Not affected

• Operating System, e.g. for Linux: Linux

$ uname -a

Linux e3ed6d449a16 6.6.113+ #1 SMP Mon Feb 2 12:27:57 UTC 2026 x86_64 x86_64 x86_64 GNU/Linux

• SDK version, e.g. for Linux:

/content# python3 --version
Python 3.12.13

/content# make --version
GNU Make 4.3
Built for x86_64-pc-linux-gnu
Copyright (C) 1988-2020 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.

/content# g++ --version
g++ (Ubuntu 11.4.0-1ubuntu1~22.04.3) 11.4.0
Copyright (C) 2021 Free Software Foundation, Inc.
This is free software; see the source for copying conditions.  There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

Failure Information (for bugs)

see above

Steps to Reproduce

On google colab free-tier

1. open terminal
2. uv pip install --system https://github.com/abetlen/llama-cpp-python/releases/download/v0.3.19/llama_cpp_python-0.3.19-cp312-cp312-linux_x86_64.whl
3. restart session

from llama_cpp import Llama

Related Issue

#1628