Sunset at Alameda Creek 12/15/2025 #bayarea #california
December 16, 2025 at 2:30 PM
Sunset at Alameda Creek 12/15/2025 #bayarea #california
It is actually possible to launch the reasoning model: DeepSeek R1 model on a Mac Mini, the hugging face community rocks, github.com/figo/llm-on-...
#deepseek #llm
#deepseek #llm
github.com
January 24, 2025 at 8:59 PM
It is actually possible to launch the reasoning model: DeepSeek R1 model on a Mac Mini, the hugging face community rocks, github.com/figo/llm-on-...
#deepseek #llm
#deepseek #llm
Continue to improve LLM on Mac Mini by integrating with langchain, the result is getting more promising, sharing the source code and detail:
github.com/figo/llm-on-...
#langchain #llm #llama-cpp #ggml
github.com/figo/llm-on-...
#langchain #llm #llama-cpp #ggml
January 20, 2025 at 10:34 PM
Continue to improve LLM on Mac Mini by integrating with langchain, the result is getting more promising, sharing the source code and detail:
github.com/figo/llm-on-...
#langchain #llm #llama-cpp #ggml
github.com/figo/llm-on-...
#langchain #llm #llama-cpp #ggml
During the holiday, I am hacking around inferencing LLM on consumer hardware: Mac Mini M4, sharing my observations github.com/figo/llm-on-...
github.com
December 30, 2024 at 4:45 PM
During the holiday, I am hacking around inferencing LLM on consumer hardware: Mac Mini M4, sharing my observations github.com/figo/llm-on-...
What are the challenges to achieve effective pod #autoscaling?
1. Adding a new k8s node takes 3-5m or more
1. Adding a new k8s node takes 3-5m or more
November 12, 2024 at 6:24 AM
What are the challenges to achieve effective pod #autoscaling?
1. Adding a new k8s node takes 3-5m or more
1. Adding a new k8s node takes 3-5m or more
November 12, 2024 at 5:43 AM