llama_cpp_sdk
First concrete self-hosted inference backend for llama.cpp, owning
llama-server boot specs, readiness probes, stop semantics, and endpoint
publication through self_hosted_inference_core.
Maintained on Hex by nshkrdotcom
Latest version
0.1.0
Last run
Aug 26, 2026
Checks
4
| Target / check | Status | Firmware size | Run |
|---|---|---|---|
|
host
host
|
pass | — | llama_cpp_sdk-0.1.0-1787744397683 |
|
nerves_system_mangopi_mq_pro
0.17.1
|
pass | 25798053 | llama_cpp_sdk-0.1.0-1787744397683 |
|
nerves_system_rpi4
2.1.1
|
pass | 42129893 | llama_cpp_sdk-0.1.0-1787744397683 |
|
nerves_system_x86_64
1.34.1
|
pass | 29535089 | llama_cpp_sdk-0.1.0-1787744397683 |
Add this badge to your README
It updates itself as llama_cpp_sdk's compatibility is reassessed.
Markdown
HTML