Kishan ,
You may want to look up :
Ø https://moonshotai.github.io/
Ø https://github.com/MoonshotAI/
Extract :
Deployment
Note
You can access Kimi K2's API on https://platform.moonshot.
The Anthropic-compatible API maps temperature by real_temperature = request_temperature * 0.6 for better compatiblity with existing applications.
Our model checkpoints are stored in the block-fp8 format, you can find it on Huggingface.
Currently, Kimi-K2 is recommended to run on the following inference engines:
- vLLM
- SGLang
- KTransformers
- TensorRT-LLM
Deployment examples for vLLM and SGLang can be found in the Model Deployment Guide.
With regards,
Hemen Parekh
No comments:
Post a Comment