good first issuerefactoringroadmap
仓库指标
- 星标
- (124,222 个星标)
- PR 合并指标
- (平均合并 6天 8小时) (30 天内合并 389 个 PR)
描述
Now that we support a large amount of architectures, we can clearly see the patterns when constructing the compute graphs - i.e. optional biases, different norm types, QKV vs Q+K+V, etc.
We should deduplicate the copy-paste portions in functions such as llm.build_llama(), llm.build_falcon(), etc.
The advantage of the current code is that it is easy to look into the graph of a specific architecture. When we refactor this, we will lose this convenience to some extend. So we should think about making this refactoring in such a way that we don't completely obscure which parts of the graph belong to which architectures
Open for ideas and suggestions how to do this best