Reproduce inference time and GPU memory of the released MMedPO medical VLMs (LLaVA-Med v1.5 + MMedPO LoRA) on VQA-RAD, SLAKE and IU-Xray - SMShovan/mmedpo-inference-benchmark ...
Thirteen interlinked handbooks for LLM inference and AI infra, in Chinese and English: Python, C++, CS, math, PyTorch, LLM internals, CUDA, training a small model from scratch, distributed ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results