Skip to content
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.

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

[BUGFix] Fix MatmulDequantize with FP4 Format #254

Merged
merged 27 commits into from
Nov 29, 2024

Conversation

LeiWang1999
Copy link
Contributor

PR Fix ref to #253 , Example:

matmul_config = bitblas.MatmulConfig(
    M=M,  # M dimension
    N=N,  # N dimension
    K=K,  # K dimension
    A_dtype=A_dtype,  # activation A dtype
    W_dtype=W_dtype,  # weight W dtype
    accum_dtype=accum_dtype,  # accumulation dtype
    out_dtype=out_dtype,  # output dtype
    layout="nt",  # matrix layout, "nt" indicates the layout of A is non-transpose and the layout of W is transpose
    propagate_b=False,  # propagate B matrix
    storage_dtype=storage_dtype,
)

matmul = bitblas.Matmul(config=matmul_config, enable_tuning=False)

@LeiWang1999 LeiWang1999 merged commit 1569c95 into microsoft:main Nov 29, 2024
6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant