ELS-RD/transformer-deploy

Issues

• convert_model command not found

  #173 opened 2 years ago by pint1022
  3

• Unable To use batching

  #180 opened a year ago by rahulmate
  1

• Encounter Error: ValueError: Message onnx.ModelProto exceeds maximum protobuf size of 2GB

  #183 opened 10 months ago by illumination-k
  0

• Occasional "CUDA error cudaErrorInvalidConfiguration:invalid configuration argument" error

  #166 opened 2 years ago by zoltan-fedor
  1

• the performance of onxx fp16 seems to be even worse than that of onnx fp32

  #182 opened a year ago by lierer007
  0

• GPTModelWrapper' object has no attribute 'can_generate'

  #177 opened a year ago by jxcomeon
  1

• Unable to optimize microsoft/deberta-v3-small model

  #150 opened 2 years ago by hlkong323
  2

• unable to host .onnx model on triton server

  #179 opened a year ago by riyaj8888
  0

• unable to do tensorrt inference

  #176 opened 2 years ago by riyaj8888
  0

• Llama support

  #170 opened 2 years ago by michaelroyzen
  2

• No supported GPU(s) detected to run this container

  #175 opened 2 years ago by sinankefeli
  0

• How to deploy TrCOR

  #163 opened 2 years ago by SShimmyo
  2

• Support converting T5 model

  #122 opened 2 years ago by ayoub-louati
  4

• transformer-deploy on triton server 22.08

  #174 opened 2 years ago by lakshaykc
  1

• Attempting to run T5 ORT model in Triton inference server

  #157 opened 2 years ago by samiur
  1

• Failed to load 'transformer_onnx_model'

  #172 opened 2 years ago by rifkybujana
  4

• Torch 2.0

  #169 opened 2 years ago by varshith15
  3

• Tokenizer path

  #171 opened 2 years ago by vishalsrao
  0

• Marginal Improvement Between INT8 and FP16

  #168 opened 2 years ago by alexriggio
  0

• I faced with Stub process is unhealthy and it will be restarted.

  #167 opened 2 years ago by OleksandrKorovii
  0

• GPT-J 6B model

  #146 opened 2 years ago by timofeev1995
  2

• sharing the code for the triton models.

  #165 opened 2 years ago by espoirMur
  0

• Zero copy may lead to wrong text generation results

  #145 opened 2 years ago by brevity2021
  6

• Can we support facebook/m2m100_418M model?

  #164 opened 2 years ago by chi2liu
  0

• ViT serving

  #162 opened 2 years ago by VoVoR
  0

• quick question about the attribute "model_name" in `BertForTokenClassification`

  #161 opened 2 years ago by yc-wang00
  0

• VDubbs

  #160 opened 2 years ago by VDubbs86
  0

• Question-Answering example not working for batch_size > 1

  #159 opened 2 years ago by lakshaykc
  0

• Support for constrained beam-search in T5

  #158 opened 2 years ago by junwang-wish
  0

• Two GPU are slower than one

  #156 opened 2 years ago by OleksandrKorovii
  0

• Tensorrt engine

  #155 opened 2 years ago by imsiddhant07
  1

• Unable to install transformer-deploy module

  #149 opened 2 years ago by elvinagam
  4

• RepositoryNotFoundError when optimizing private HF model

  #148 opened 2 years ago by Matthieu-Tinycoaching
  0

• OpusMT conversion

  #143 opened 2 years ago by Matthieu-Tinycoaching
  1

• Embedding with T5-Encoder

  #153 opened 2 years ago by DA-L3
  1

• How to create custom image with transformers pre-installed?

  #147 opened 2 years ago by tamaghna-dutta
  0

• encoder_hidden_states in the onnx inputs

  #139 opened 2 years ago by pngmafia
  3

• TypeError: unhashable type: 'slice'

  #136 opened 2 years ago by pngmafia
  2

• [Question] Converting models over 2GB

  #138 opened 2 years ago by wkkautas
  3

• Does the text generation instructions work for the ByT5 models? (byte-by-byte T5)?

  #140 opened 2 years ago by NOT-HAL9000
  1

• Using t5-large in t5 notebook, the translation result is invalid

  #135 opened 2 years ago by brevity2021
  1

• Failed to load private model

  #132 opened 2 years ago by Matthieu-Tinycoaching
  5

• t5 notebook broken with transformer-deploy 0.5.0

  #130 opened 2 years ago by michaelroyzen
  3

• [Question] Documentation for generative model API and parameters?

  #129 opened 2 years ago by tanmayb123
  1

• [Question] Batch inference for classification models

  #128 opened 2 years ago by denisov-vlad
  3

• Unable to pull docker image

  #127 opened 2 years ago by brevity2021
  1

• TypeError: deserialize_cuda_engine(): incompatible function arguments.

  #126 opened 2 years ago by harishprabhala
  0

• GPU quantization for sentence-transformer: ONNX quantized model

  #124 opened 2 years ago by Matthieu-Tinycoaching
  3

• How to Run With Polygraphy Graph Surgeon

  #121 opened 2 years ago by sam-h-bean
  5

• Question about generative model notebook

  #123 opened 2 years ago by hyunwoongko
  1