Releases: lucidrains/vector-quantize-pytorch
Releases Β· lucidrains/vector-quantize-pytorch
0.10.9
fix quantize dropout logic in rq
0.10.8
support masking, for phenaki
0.10.7
support masking, for phenaki
0.10.6
0.10.6
0.10.5
add quantizer dropout, for soundstream training
0.10.4
fix a "Tensor need to be contiguous" error in nccl distributed training
0.10.3
break out a function needed for audiolm
0.10.2
fix bug with sample_vectors_distributed, needed for kmeans init in diβ¦
0.10.1
only allow for syncing kmeans with single codebooks, also allow for tβ¦
0.10.0
add ability to fetch all codes across all quantization layers in RQ, β¦