Instructions to use nics-efc/C2C_Fuser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nics-efc/C2C_Fuser with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nics-efc/C2C_Fuser")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nics-efc/C2C_Fuser", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use nics-efc/C2C_Fuser with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nics-efc/C2C_Fuser" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nics-efc/C2C_Fuser", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nics-efc/C2C_Fuser
- SGLang
How to use nics-efc/C2C_Fuser with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "nics-efc/C2C_Fuser" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nics-efc/C2C_Fuser", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "nics-efc/C2C_Fuser" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nics-efc/C2C_Fuser", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nics-efc/C2C_Fuser with Docker Model Runner:
docker model run hf.co/nics-efc/C2C_Fuser
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,12 @@ tags:
|
|
| 7 |
- agent
|
| 8 |
- communication
|
| 9 |
arxiv: 2510.03215
|
| 10 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
- agent
|
| 8 |
- communication
|
| 9 |
arxiv: 2510.03215
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
This is the C2C Fuser used by the paper [Cache-to-Cache: Direct Semantic Communication Between Large Language Models](https://huggingface.co/papers/2510.03215).
|
| 13 |
+
|
| 14 |
+
Cache-to-Cache (C2C) enables Large Language Models to communicate directly through their KV-Caches, bypassing text generation.
|
| 15 |
+
|
| 16 |
+
Please visit our [GitHub repo](https://github.com/thu-nics/C2C) for more information.
|
| 17 |
+
|
| 18 |
+
Project page: [https://fuvty.github.io/C2C_Project_Page/](https://fuvty.github.io/C2C_Project_Page/)
|