Use gemini plugin and LowLevelZero to run llama2_7b. In the pulgin in gemini, set the policy to static, shard_param_frac, offload_optim_frac, and offload_param_frac to 0.0, making gemini equal to zero2, and set stage to 2 in LowLevelZero. Using bf16 for training, and comparing the two plugins, we found that the GPU memory usage of gemini is higher than that of LowLevelZero. Why is this? In principle, gemini should save more GPU memory

[JJGSBGQ]

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

Title: Use gemini plugin and LowLevelZero to run llama2_7b. In the pulgin in gemini, set the policy to static, shard_param_frac, offload_optim_frac, and offload_param_frac to 0.0, making gemini equal to zero2, and set stage to 2 in LowLevelZero. Using bf16 for training, and comparing the two plugins, we found that the memory usage of gemini is higher than that of LowLevelZero. Why is this? In principle, gemini should save more video memory

[JJGSBGQ]

When perform stable-diffusion in the same way, find that gemni has a lower GPU memory usage than LowLevelZero