transformers
69fd225a - Enable mxfp4 model on CPU (#43512)

Commit
52 days ago
Enable mxfp4 model on CPU (#43512) * enable mxfp4 on CPU Signed-off-by: jiqing-feng <jiqing.feng@intel.com> * test mxfp4 Signed-off-by: jiqing-feng <jiqing.feng@intel.com> * revert error change Signed-off-by: jiqing-feng <jiqing.feng@intel.com> * fix mxfp4 device check Signed-off-by: jiqing-feng <jiqing.feng@intel.com> * fix mxfp4 check Signed-off-by: jiqing-feng <jiqing.feng@intel.com> * update tests Signed-off-by: jiqing-feng <jiqing.feng@intel.com> * add cpu dispatch Signed-off-by: jiqing-feng <jiqing.feng@intel.com> * update mxfp4 kernel check Signed-off-by: jiqing-feng <jiqing.feng@intel.com> * dequantize mxfp4 model if don't use kernels on CPU Signed-off-by: jiqing-feng <jiqing.feng@intel.com> * rm comments Signed-off-by: jiqing-feng <jiqing.feng@intel.com> --------- Signed-off-by: jiqing-feng <jiqing.feng@intel.com> Co-authored-by: Mohamed Mekkouri <93391238+MekkCyber@users.noreply.github.com>
Author
Parents
Loading