Skip to content

Conversation

@tazlin
Copy link
Member

@tazlin tazlin commented Nov 25, 2025

  • Enhanced quantization pattern matching in text_model_parser.py to support legacy formats (Q*_0, Q*_1).
  • Updated IndexedHordeModelStats to aggregate statistics across all quantization variants and org-prefixed model names by building a base name index.
  • Added tests to verify correct aggregation and grouping of stats and model variants, including case-insensitivity and prevention of double-counting.

tazlin and others added 2 commits November 25, 2025 11:55
- Enhanced quantization pattern matching in text_model_parser.py to support legacy formats (Q*_0, Q*_1).
- Updated IndexedHordeModelStats to aggregate statistics across all quantization variants and org-prefixed model names by building a base name index.
- Added tests to verify correct aggregation and grouping of stats and model variants, including case-insensitivity and prevention of double-counting.

lint: fix
@tazlin tazlin merged commit e8c3a60 into main Nov 25, 2025
20 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants