Skip to content

ADFA-5188 | Enable KV cache quantization and flash attention - #76

Open
jatezzz wants to merge 15 commits into
mainfrom
fix/ADFA-5188-kv-cache-quantization
Open

ADFA-5188 | Enable KV cache quantization and flash attention#76
jatezzz wants to merge 15 commits into
mainfrom
fix/ADFA-5188-kv-cache-quantization

merge: bring the squashed ADFA-5187 into the q8_0 KV cache branch

78f9300
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar