Actions: ggml-org/llama.cpp
Actions
6,862 workflow run results
6,862 workflow run results
server: add --reasoning-budget 0 to disable thinking (incl. qwen3 w/ enable_thinking:false)
CI
#22899:
Pull request #13771
opened
by
ochafik
server: streaming of tool calls and thoughts when --jinja is on (…
CI
#22892:
Commit f5cd27b
pushed
by
ochafik