 Jesse
|
88021565f0
chat : Deepseek V3.1 reasoning and tool calling support (OpenAI Style) (#15533)
|
4 bulan lalu |
 Sam
|
ef0144c087
model: support GLM 4.5 family of models (#14939)
|
5 bulan lalu |
 Olivier Chafik
|
e121edc432
`server`: add `--reasoning-budget 0` to disable thinking (incl. qwen3 w/ enable_thinking:false) (#13771)
|
7 bulan lalu |
|
Olivier Chafik
|
f5cd27b71d
`server`: streaming of tool calls and thoughts when `--jinja` is on (#12379)
|
7 bulan lalu |
 Olivier Chafik
|
669912d9a5
`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)
|
10 bulan lalu |
|
Olivier Chafik
|
c7f460ab88
`server`: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless `--reasoning-format none` (#11607)
|
11 bulan lalu |
