xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 08:24:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update kimi-k2 tool calling docs, enable unit tests (#20821)

Browse Source 
Signed-off-by: wangzhengtao <wangzhengtao@moonshot.cn>
Co-authored-by: wangzhengtao <wangzhengtao@moonshot.cn>
Co-authored-by: wangzhengtao <wangzhengtao@msh.team>
This commit is contained in:
bigmoyan 2025-07-12 04:16:14 +08:00 committed by GitHub
parent 0d21b2664c
commit 5f0af36af5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docs/features/tool_calling.md
View File

@ -282,6 +282,14 @@ Supported models:
Flags: `--tool-call-parser deepseek_v3 --chat-template {see_above}`
### Kimi-K2 Models (`kimi_k2`)
Supported models:
* `moonshotai/Kimi-K2-Instruct`
Flags: `--tool-call-parser kimi_k2`
### Models with Pythonic Tool Calls (`pythonic`)
A growing number of models output a python list to represent tool calls instead of using JSON. This has the advantage of inherently supporting parallel tool calls and removing ambiguity around the JSON schema required for tool calls. The `pythonic` tool parser can support such models.

2
tests/tool_use/test_kimi_k2_tool_parser.py
View File

@ -10,8 +10,6 @@ from vllm.entrypoints.openai.protocol import FunctionCall, ToolCall
from vllm.entrypoints.openai.tool_parsers import KimiK2ToolParser
from vllm.transformers_utils.tokenizer import get_tokenizer
pytest.skip("skip kimi_k2 parser test", allow_module_level=True)
# Use a common model that is likely to be available
MODEL = "moonshotai/Kimi-K2-Instruct"