executorch icon indicating copy to clipboard operation
executorch copied to clipboard

On-device AI across mobile, embedded and edge for PyTorch

Results 597 executorch issues
Sort by recently updated
recently updated
newest added

Summary: Identify builds with kv cache Differential Revision: D54300827

CLA Signed
fb-exported

Summary: Add warning if a seemingly fairseq2 checkpoint is passed to model constructor but --fairseq2 was not specified. (Heuristic.) Differential Revision: D54209318

CLA Signed
fb-exported

Summary: Resolve recurring errors where query is c10::Half and key and value float. This should ideally work from first principles, but somehow it does not. We need to fix the...

CLA Signed
fb-exported

Summary: Add options for embedding quantization: bitwidth, group_size on CLI Differential Revision: D54159472

CLA Signed
fb-exported

Summary: pow(n,2) => n*n Differential Revision: D54142779

CLA Signed
fb-exported

Summary: improvements: asymmetric group size less militant checking out_dtype added Differential Revision: D53990647

CLA Signed
fb-exported

Summary: Add debug info to op_embedding Differential Revision: D54047417

CLA Signed
fb-exported

Summary: Add embedding op to llama build Reviewed By: shoumikhin Differential Revision: D53985792

CLA Signed
fb-exported

Summary: improvements: asymmetric group size less militant checking out_dtype added legacy compatibility Differential Revision: D54074895

CLA Signed
fb-exported

Summary: Compute size and bleu score for different quantization combinations Reviewed By: mavlyutovr Differential Revision: D53687784

CLA Signed
fb-exported