Popular repositories Loading

1. hf_vram_calc hf_vram_calc Public

   A CLI tool for estimating GPU VRAM requirements for Hugging Face models, supporting various data types, parallelization strategies, and fine-tuning scenarios like LoRA.

   Python 1 2

2. mem_scan mem_scan Public

   A command-line tool for monitoring host and device GPU memory usage, suitable for observing runtime memory characteristics during program execution.

   Python

3. safetensors_exp safetensors_exp Public

   safetensors_exp

4. TensorRT-Model-Optimizer TensorRT-Model-Optimizer Public

   Forked from NVIDIA/TensorRT-Model-Optimizer

   A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment…

   Python