Unverified Commit cf9a7c2f authored by Phuong Nguyen's avatar Phuong Nguyen Committed by GitHub
Browse files

[JAX] Refactor + MXFP8 + GroupedGEMM (#1627)



* refactor + mxfp8

* added grouped gemm

* rename linear to dense

* added cublas init phase for groupedGemm

* relax the tol of test encoder multiprocessing mxfp8 by 0.001
Signed-off-by: default avatarPhuong Nguyen <phuonguyen@nvidia.com>

---------
Signed-off-by: default avatarPhuong Nguyen <phuonguyen@nvidia.com>
Co-authored-by: default avatarHua Huang <huah@nvidia.com>
Co-authored-by: default avatarJeremy Berchtold <jberchtold@nvidia.com>
parent be055eb0
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment