run DeepSeek-R1 GGUFs on KTransformers
-
Updated
Mar 3, 2025 - Python
#
ktransformers
Here are 3 public repositories matching this topic...
LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features an efficient GPU parallel and NUMA parallel architecture, supporting hybrid inference for MOE large models.
-
Updated
Nov 8, 2025 - Python
清华大学 KTransformers Docker Image Build Tool
docker docker-compose docker-container docker-image deepseek-coder deepseek-chat deepseek-llm deepseek deepseek-math deepseek-api deepseek-v3 deepseek-r1 deepseek-r1-zero deepseek-ai ktransformers
-
Updated
Apr 20, 2025 - Dockerfile
Improve this page
Add a description, image, and links to the ktransformers topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the ktransformers topic, visit your repo's landing page and select "manage topics."