Skip to content

Update README.md #37

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
liuhao-97 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update README.md #37

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 18 additions & 18 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,34 +144,34 @@ specs like w\_elem\_format\_bp.
# MXFP8_e5m2 matmuls with bfloat16 vector ops, forward pass only
mx_specs = MxSpecs()

mx_specs[‘scale_bits’] = 8
mx_specs[‘w_elem_format’] = 'fp8_e5m2'
mx_specs[‘a_elem_format’] = 'fp8_e5m2'
mx_specs[‘block_size’] = 32
mx_specs[‘bfloat’] = 16
mx_specs[‘custom_cuda’] = True
mx_specs['scale_bits'] = 8
mx_specs['w_elem_format'] = 'fp8_e5m2'
mx_specs['a_elem_format'] = 'fp8_e5m2'
mx_specs['block_size'] = 32
mx_specs['bfloat'] = 16
mx_specs['custom_cuda'] = True
```
```
# MXFP4_e2m1 matmuls with bfloat16 vector ops, forward pass only
mx_specs = MxSpecs()

mx_specs[‘scale_bits’] = 8
mx_specs[‘w_elem_format’] = 'fp4_e2m1'
mx_specs[‘a_elem_format’] = 'fp4_e2m1'
mx_specs[‘block_size’] = 32
mx_specs[‘bfloat’] = 16
mx_specs[‘custom_cuda’] = True
mx_specs['scale_bits'] = 8
mx_specs['w_elem_format'] = 'fp4_e2m1'
mx_specs['a_elem_format'] = 'fp4_e2m1'
mx_specs['block_size'] = 32
mx_specs['bfloat'] = 16
mx_specs['custom_cuda'] = True
```
```
# MXINT8 matmuls with bfloat16 vector ops, forward pass only
mx_specs = MxSpecs()

mx_specs[‘scale_bits’] = 8
mx_specs[‘w_elem_format’] = 'int8'
mx_specs[‘a_elem_format’] = 'int8'
mx_specs[‘block_size’] = 32
mx_specs[‘bfloat’] = 16
mx_specs[‘custom_cuda’] = True
mx_specs['scale_bits'] = 8
mx_specs['w_elem_format'] = 'int8'
mx_specs['a_elem_format'] = 'int8'
mx_specs['block_size'] = 32
mx_specs['bfloat'] = 16
mx_specs['custom_cuda'] = True
```

### Backward Pass Quantization ###
Expand Down