Skip to content

Quantize Gemma4 per-layer embedding tables for WebGPU (INT4/INT8 configurable) - #403

Draft
feich-ms wants to merge 6 commits into
mainfrom
user/feich/quantize_per_layer_embedding_table
Draft

Quantize Gemma4 per-layer embedding tables for WebGPU (INT4/INT8 configurable)#403
feich-ms wants to merge 6 commits into
mainfrom
user/feich/quantize_per_layer_embedding_table

Isolate Gemma4 per-layer embedding quantization

839ccf3
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar