biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Feature] Support MiniMax-M1 function calls features (#20297)

Browse Source 
Signed-off-by: QscQ <qscqesze@gmail.com>
Signed-off-by: qingjun <qingjun@minimaxi.com>
This commit is contained in:
qscqesze
2025-07-03 14:48:27 +08:00
committed by GitHub
parent 4ff61ababa
commit 363528de27
5 changed files with 842 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
docs/features/tool_calling.md
View File

@@ -264,6 +264,15 @@ For Qwen2.5, the chat template in tokenizer_config.json has already included sup
Flags: `--tool-call-parser hermes`
### MiniMax Models (`minimax_m1`)
Supported models:
* `MiniMaxAi/MiniMax-M1-40k` (use with <gh-file:examples/tool_chat_template_minimax.jinja>)
* `MiniMaxAi/MiniMax-M1-80k` (use with <gh-file:examples/tool_chat_template_minimax.jinja>)
Flags: `--tool-call-parser minimax --chat-template examples/tool_chat_template_minimax.jinja`
### DeepSeek-V3 Models (`deepseek_v3`)
Supported models: