transformers
Finegrained FP8 v4: fused grouepd/batched
#46957
Open
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
8
Changes
View On
GitHub
Commits
v4
IlyasMoutawwakil
committed
114 days ago
rename
IlyasMoutawwakil
committed
114 days ago
support swiglu stuff
IlyasMoutawwakil
committed
112 days ago
Merge branch 'main' into finegrained-fp8-v4
IlyasMoutawwakil
committed
112 days ago
scale fmt with mxfp8
IlyasMoutawwakil
committed
112 days ago
honor the dtype
IlyasMoutawwakil
committed
112 days ago
fix vision tower quantization
IlyasMoutawwakil
committed
112 days ago
avoid cache to avoid dynamo thrashing warnings
IlyasMoutawwakil
committed
112 days ago
Loading