tensorops/TransformerX

Issues

• [BUG] SinePositionalEncoding

  #115 opened 5 months ago by soran-ghaderi
  0

• MultiheadAttention: Add support for distributed computation

  #84 opened 2 years ago by soran-ghaderi
  0

• New feedforward layers

  #43 opened 2 years ago by soran-ghaderi
  0

• [issue] Create issue template forms

  #109 opened a year ago by soran-ghaderi
  0

• New attention masking layers

  #86 opened 2 years ago by soran-ghaderi
  0

• Dilated

  #87 opened 2 years ago by soran-ghaderi
  0

• Docs for the decoder block

  #90 opened 2 years ago by soran-ghaderi
  0

• New embedding layers

  #41 opened 2 years ago by soran-ghaderi
  0

• Handle input arguments and raise exceptions

  #31 opened 2 years ago by soran-ghaderi
  2

• New residual and residual gate layers

  #42 opened 2 years ago by soran-ghaderi
  0

• New attention layers

  #44 opened 2 years ago by soran-ghaderi
  0

• Test cases for the layers

  #63 opened 2 years ago by soran-ghaderi
  0

• [Issue] Quantization support

  #108 opened a year ago by soran-ghaderi
  0

• Documentation - Readme

  #29 opened 2 years ago by soran-ghaderi
  1

• [Enhancement] Provide examples of how to use TransformerX

  #112 opened 10 months ago by soran-ghaderi
  0

• Encoder-only Classifier

  #113 opened 10 months ago by soran-ghaderi
  0

• Masking system and general RC additions

  #106 opened 10 months ago by soran-ghaderi
  0

• [Enhancement] KV Caching for inference speed

  #110 opened 10 months ago by soran-ghaderi
  1

• [doc] TransformerEncoder

  #102 opened 2 years ago by soran-ghaderi
  0

• [Tests] TransformerEncoder

  #100 opened 2 years ago by soran-ghaderi
  0

• [Issue] Refactor the TransformerEncoder layer

  #99 opened 2 years ago by soran-ghaderi
  0

• [tests] TransformerDecoderBlock

  #96 opened 2 years ago by soran-ghaderi
  0

• Documentation

  #30 opened 2 years ago by soran-ghaderi
  2

• TransformerEncoder

  #57 opened 2 years ago by soran-ghaderi
  0

• [tests] TransformerEncoderBlock

  #95 opened 2 years ago by soran-ghaderi
  0

• Readme updated information

  #93 opened 2 years ago by soran-ghaderi
  0

• Refactor transformer decoder block

  #89 opened 2 years ago by soran-ghaderi
  0

• Refacor TransformerEncoderBlock

  #77 opened 2 years ago by soran-ghaderi
  0

• MultiHeadAttention #31

  #37 opened 2 years ago by soran-ghaderi
  0

• Refactor DotProductAttention layer

  #80 opened 2 years ago by soran-ghaderi
  0

• PositionwiseFFN

  #82 opened 2 years ago by soran-ghaderi
  0

• DotProductAttention

  #67 opened 2 years ago by soran-ghaderi
  0

• Refactor implementation - AbsolutePositionalEncoding class

  #71 opened 2 years ago by soran-ghaderi
  0

• Refactor softmax_attention

  #78 opened 2 years ago by soran-ghaderi
  0

• PositionalEncoding

  #70 opened 2 years ago by soran-ghaderi
  0

• PositionWiseFFN advanced features

  #73 opened 2 years ago by soran-ghaderi
  0

• AddNorm advanced features

  #75 opened 2 years ago by soran-ghaderi
  0

• AddNorm

  #65 opened 2 years ago by soran-ghaderi
  0

• MultiHeadAttention

  #64 opened 2 years ago by soran-ghaderi
  1

• TransformerDecoder

  #59 opened 2 years ago by soran-ghaderi
  0

• TransformerDecoderBlock

  #52 opened 2 years ago by soran-ghaderi
  0

• TransformerEncoderBlock

  #51 opened 2 years ago by soran-ghaderi
  0

• PositionwiseFFN

  #49 opened 2 years ago by soran-ghaderi
  0

• Rename PositionalEncoding to AbsolutePositionalEmbedding

  #47 opened 2 years ago by soran-ghaderi
  0

• PositionalEncoding

  #46 opened 2 years ago by soran-ghaderi
  0

• MultiHeadAttention #30

  #36 opened 2 years ago by soran-ghaderi
  0

• Readme typo

  #28 opened 2 years ago by soran-ghaderi
  0

• DotProductAttention docs #30

  #33 opened 2 years ago by soran-ghaderi
  0

• AddNorm docs #30

  #32 opened 2 years ago by soran-ghaderi
  0

• AddNorm #31

  #34 opened 2 years ago by soran-ghaderi
  0