@MiaAI_lab all I want for Christmas is a frontier LLM that I can run on two DGX Sparks! Ho ho ho
- Starting today, no more frontier models for me. They can take their rate limiting and ...
- Is anyone working to add .gguf support to vLLM? I hate the tensor files, hard to backup. Dont want 50 files in a hidden folder when one visible gguf file will do. I have like 5 days trying to get minimax/deepseek to do it in dgx spark.
- Asking Santa Claus early to bring me tokens without rate limits