Skip to content

Misc. bug: -lv missing trace in --help, trace logs use I instead of T #23290

@Kangaroux

Description

@Kangaroux

Name and Version

$ ./llama-b9209/llama-server --version
version: 9209 (0caf2a1d4)
built with GNU 11.4.0 for Linux x86_64

Operating systems

Linux

Which llama.cpp modules do you know to be affected?

llama-server

Command line

./llama-server --help
./llama-server -lv 4 -m ...

Problem description & steps to reproduce

Trace is missing from the --help output. 4=trace, 5=debug

-lv,   --verbosity, --log-verbosity N   Set the verbosity threshold. Messages with a higher verbosity will be
                                        ignored. Values:
                                         - 0: generic output
                                         - 1: error
                                         - 2: warning
                                         - 3: info
                                         - 4: debug
                                        (default: 3)

Additionally, trace logs have the I prefix (for info) instead of T (for trace).

First Bad Commit

Introduced in #23021

Relevant log output

Logs
0.00.217.912 I common_params_print_info: build 9209 (0caf2a1d4) with GNU 11.4.0 for Linux x86_64
0.00.217.915 I log_info: verbosity = 4 (adjust with the `-lv N` CLI arg)
0.00.217.915 I device_info:
0.00.218.089 I   - Vulkan0 : Radeon RX 7900 XTX (RADV NAVI31) (24576 MiB, 23368 MiB free)
0.00.218.093 I   - CPU     : AMD Ryzen 7 5700X3D 8-Core Processor (31996 MiB, 31996 MiB free)
0.00.218.121 I system_info: n_threads = 8 (n_threads_batch = 8) / 16 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 | 
0.00.218.363 I srv          init: running without SSL
0.00.218.638 I srv          init: using 15 threads for HTTP server
0.00.219.093 I srv         start: binding port with default address family
0.00.220.235 I srv          main: loading model
0.00.220.245 I srv    load_model: loading model '/home/jessie/llamacpp/models/Qwen3.6-27B-UD-Q5_K_XL.gguf'
0.00.220.275 I common_init_result: fitting params to device memory ...
0.00.220.276 I common_init_result: (for bugs during this step try to reproduce them with -fit off, or provide --verbose logs if the bug only occurs with -fit on)

--- trace logs below, incorrect prefix ---

0.00.220.283 I common_params_fit_impl: getting device memory data for initial parameters:
0.00.276.926 I llama_model_loader: loaded meta data with 52 key-value pairs and 866 tensors from /home/jessie/llamacpp/models/Qwen3.6-27B-UD-Q5_K_XL.gguf (version GGUF V3 (latest))
0.00.276.955 I llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.

Metadata

Metadata

Assignees

No one assigned

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions