`server`: add `--reasoning-budget 0` to disable thinking (incl. qwen3 w/ enable_thinking:false)#13771

Merged

ochafik merged 13 commits intoggml-org:masterfrom

ochafik:enable-thinking

May 25, 2025

Commits on May 25, 2025

server: fix/test add_generation_prompt
ochafik
committed
8a25f79
Copy full SHA for 8a25f79
tools: enable hermes2/qwen chat logic even w/o tools
ochafik
committed
43b5626
Copy full SHA for 43b5626
server: add --reasoning-format=disabled to disable thinking (incl. qwen3 w/ enable_thinking:false)
ochafik
committed
b457f89
Copy full SHA for b457f89
Update README.md
ochafik
committed
df25e6b
Copy full SHA for df25e6b
Add models/templates/Qwen-Qwen3-0.6B.jinja
ochafik
committed
b6eb0a5
Copy full SHA for b6eb0a5
update --reasoning-format={disabled -> nothink} as suggested
ochafik
committed
cdea6a9
Copy full SHA for cdea6a9
fix command r7b's nothink w/ official template
ochafik
committed
473c01e
Copy full SHA for 473c01e
rewrite docs as list as suggested
ochafik
committed
6b9efe7
Copy full SHA for 6b9efe7
Update common/chat.cpp
Show description for 355b38c

ochafik
and
ngxson
authored
355b38c
Copy full SHA for 355b38c
Merge branch 'enable-thinking' of github.com:ochafik/llama.cpp into enable-thinking
ochafik
committed
fe6022f
Copy full SHA for fe6022f
const char* return for chat enum name helpers
ochafik
committed
8547fcc
Copy full SHA for 8547fcc
switch to --reasoning-budget flag
ochafik
committed
9cdeebe
Copy full SHA for 9cdeebe
Merge branch 'fix-gen-prompt' into enable-thinking
ochafik
committed
9162380
Copy full SHA for 9162380