Skip to content

fix(#4621): QK-norm models take the FP16 batched prefill when it fits (D3-SPLIT B, stacked on #4620) - #4624

Closed
noahgift wants to merge 7 commits into
ec/3715-lambda-cellsfrom
ec/4621-fit-and-chat-kv
Closed

fix(#4621): QK-norm models take the FP16 batched prefill when it fits (D3-SPLIT B, stacked on #4620)#4624
noahgift wants to merge 7 commits into
ec/3715-lambda-cellsfrom
ec/4621-fit-and-chat-kv

Merge A (ec/3715-lambda-cells @17f499b4b5) into B

2325555
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar