[Tracing] Skip non-ancestors of sequential targets

[kylesayrs]

Purpose

• Reduce model support burden by skipping any modules which are not call graph ancestors of the sequential targets
• Rather than requiring the user to specify a list of ignored modules, only trace what is necessary to disjointly execute sequential targets
  • In the future, the ignore field will be used to skip untraceable function/method names
• This change does not change functionality because all ignored modules are already non-ancestors of sequential targets

Changes

• Remove ignore modules requirement (all ignored modules are already non-ancestors of sequential targets)
• Implement get_sequential_ancestors which returns all ancestors of the sequential targets
• Modify tracer to skip anything that is not a sequential ancestor or has offloaded modules
  • The two sets rarely overlap, and when they do, the module is skipped for safety and the user is warned

Testing

• Added tests for get_sequential_ancestors
• [Tracing][Testing] Add tracing tests #1335

Follow ups

• [Tracing] Autowrap methods by name #1390

[github-actions]

👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review.

Note: This is required to complete the testing suite, please only add the label once the PR is code complete and local testing has been performed.

[brian-dellabetta]

cool!

[shanjiaz]

DFS logic looks good to me! Should we update this guide now that we automatically handles ignore?

[kylesayrs]

@shanjiaz I'm waiting to do that after #1390 lands, since at that point, ignore will become tracing_ignore and will ignore function names, not modules

[shanjiaz]

Looks good to me! Thanks for answering my tracer questions