Quantize Gemma4 per-layer embedding tables for WebGPU (INT4/INT8 configurable) - #403
Quantize Gemma4 per-layer embedding tables for WebGPU (INT4/INT8 configurable)#403feich-ms wants to merge 6 commits into
7 new alerts
New alerts in code changed by this pull request
- 7 warnings
See annotations below for details.
Annotations
Check warning on line 328 in src/mobius/_configs/_base.py
Code scanning / lintrunner
RUFF/F401 Warning
Check warning on line 328 in src/mobius/_configs/_base.py
Code scanning / lintrunner
RUFF/RUF102 Warning
Check warning on line 343 in src/mobius/_configs/_base.py
Code scanning / lintrunner
RUFF/F401 Warning
Check warning on line 343 in src/mobius/_configs/_base.py
Code scanning / lintrunner
RUFF/RUF102 Warning
Check warning on line 1138 in src/mobius/_weight_utils_test.py
Code scanning / lintrunner
RUFF/D403 Warning
Check warning on line 1175 in src/mobius/_weight_utils_test.py
Code scanning / lintrunner
RUFF/RUF059 Warning
Check warning on line 1175 in src/mobius/_weight_utils_test.py
Code scanning / lintrunner
RUFF/RUF059 Warning