Skip to content

[WebGPU] Add int8 kv cache block quantization - #32284

Merged
Sushanth Rajasankar (sushraja-msft) merged 14 commits into
mainfrom
user/sushraja/q8_kv_cache
Sep 8, 2026
Merged

Sushanth Rajasankar (sushraja-msft) merged 14 commits into
mainfrom
user/sushraja/q8_kv_cache

Add interleaved rotary fallback and validation for Q8 block quantizat…

8c67fd6
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar