RahulSChand/gpu_poor Issues
Activation Memory
ClosedMissing License
Updatedcompute in gpu_configs.json meaning
Updated 1DeepSpeed support
Closed 1Test results are different
Closed 6API to use this repo
Updated 1
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization