About 6 results
Open links in new tab
  1. mamba/mamba_ssm/modules/mamba2.py at main - GitHub

    # TODO: What if batch size changes between generation, and we reuse the same states?

  2. Is there a small model trainer? · Issue #24 · state-spaces/mamba

    Dec 6, 2023 · You will be able to reuse this secret in all of your notebooks. Please note that authentication is recommended but still optional to access public models or datasets. …

  3. mamba/mamba_ssm/modules/mamba_simple.py at main · state ... - GitHub

    # TODO: What if batch size changes between generation, and we reuse the same states?

  4. Fixes and Enhancements for Mamba Inference and Reference ...

    This pull request addresses several bugs and limitations within the Mamba codebase, primarily aimed at improving inference robustness in the Mamba2 module and increasing the accuracy …

  5. If batchsize is large (ex.4096), this mamba implementation works …

    Apr 9, 2024 · # TODO: What if batch size changes between generation, and we reuse the same states? if initialize_states: conv_state.zero_() ssm_state.zero_() return conv_state, ssm_state …