google-deepmind / google-deepmind/spectral_ssm

step helper

Open
#1 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
36
Forks
6
PR merge metrics
No merged PRs in 30d

Description

Would you have an idea how one can adapt the code to be able to do auto-regressive steps (for inference)? Is the fact that the `input_len` is fixed an issue?

Contributor guide

Open the contributing guide

Research direction

Start by reading the repository's Python implementation and the code that uses input_len for inference. Determine how auto-regressive steps should work when input_len is fixed, then define a concrete completion criterion for supporting inference-time stepping and validate it with the repository's existing checks.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.