Name and Version
llama-server 5803c8d
Operating systems
Linux
Which llama.cpp modules do you know to be affected?
llama-server
Command line
srv load: spawning server instance with args:
srv load: /app/llama-server
srv load: --host
srv load: 127.0.0.1
srv load: --jinja
srv load: --no-mmproj-auto
srv load: --port
srv load: 39547
srv load: --slot-save-path
srv load: /config/slots
srv load: --temperature
srv load: 1.0
srv load: --top-k
srv load: 64
srv load: --top-p
srv load: 0.95
srv load: --webui
srv load: --webui-config-file
srv load: /config/webui-config.json
srv load: --webui-mcp-proxy
srv load: --alias
srv load: unsloth/gemma-4-26B-A4B-GGUF:Q5_K_XL
srv load: --batch-size
srv load: 2048
srv load: --ctx-size
srv load: 16000
srv load: --checkpoint-every-n-tokens
srv load: 2048
srv load: --cache-type-k
srv load: q8_0
srv load: --cache-type-v
srv load: q8_0
srv load: --flash-attn
srv load: on
srv load: --hf-repo
srv load: unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q5_K_XL
srv load: --n-gpu-layers
srv load: -1
srv load: --parallel
srv load: 1
srv load: --ubatch-size
srv load: 2048
Problem description & steps to reproduce
Using Gemma4 and tool calling I get the following response back. It is not 100% clear to me if this is a parser issue and these should be removed or if we just need to filter them out
{
"area": "Main Bedroom",
"domain": "[<|\"|>light<|\"|>]",
"name": "Bedroom Lights"
}
First Bad Commit
No response
Relevant log output
Logs
{
"area": "Main Bedroom",
"domain": "[<|\"|>light<|\"|>]",
"name": "Bedroom Lights"
}
Name and Version
llama-server 5803c8d
Operating systems
Linux
Which llama.cpp modules do you know to be affected?
llama-server
Command line
Problem description & steps to reproduce
Using Gemma4 and tool calling I get the following response back. It is not 100% clear to me if this is a parser issue and these should be removed or if we just need to filter them out
First Bad Commit
No response
Relevant log output
Logs