Warning(s) when starting rLLM-cpp

[Devis Lucato]

Steps

cd rllm-cpp
./cpp-server.sh phi2

Result

• The server builds and starts
• The log contains one warning: WARN [llama_cpp_low] llm_load_vocab: mismatch in special tokens definition ( 910/51200 vs 944/51200 )
• This log entry looks like a warning but is logged as INFO 7 times: INFO [hf_hub] Token file not found "/Users/tester/.cache/huggingface/token"

System

• system: macOS 14.3, Apple M3
• cargo 1.75.0
• cmake version 3.28.2
• ccache version 4.9

[Michał Moskal]

The token warning comes from llama.cpp; not sure what can we do about it.

The hf_hub info is only relevant if there is a "permission denied" afterwards (eg for some of the Meta models).