aws-neuron/aws-neuron-sdk

Issues

• Is there something wrong in torch_neuronx.trace ?

  #907 opened 17 days ago by mhokchuekchuek
  3

• AWS NeuronX sdk installation

  #916 opened 7 days ago by Zkarape
  2

• Bad image quality for Stable Diffusion 1.5 after applying the optimized attenstion score

  #897 opened 5 days ago by JingyaHuang
  4

• DataParallel Support on CRF inference

  #914 opened 8 days ago by jyang-aws
  1

• neuron-distributed for inference

  #915 opened 8 days ago by sonic182
  1

• ECS inf1 neuron hook script fails

  #911 opened 14 days ago by rantoniuk
  2

• Input tensors not being read torch neuronx 2.1.2

  #906 opened 8 days ago by PrateekAg1511
  4

• Model doesn't support task text-classification for the neuron backend

  #913 opened 9 days ago by ldoff-tech42
  0

• Issue on page /frameworks/torch/torch-neuronx/programming-guide/training/pytorch-neuron-programming-guide.html

  #912 opened 10 days ago by yahavb
  0

• Is it possible to compile a model when no NeuronCores are available?

  #910 opened 15 days ago by CozyDoomer
  2

• Compilation Error with torch_neuronx.trace on EC2 inf2.xlarge

  #883 opened 2 months ago by SergioMartinezAvahitech
  5

• support for aten::upsample_nearest3d

  #908 opened 17 days ago by SimonRelu
  0

• Quite largely increased latency with weights/neff separated

  #905 opened 22 days ago by JingyaHuang
  1

• Input tensor is not an XLA tensor: CPUFloatType while using crf.decode function

  #901 opened 24 days ago by PrateekAg1511
  4

• PDF print on the home page is empty when the left side is collapsed

  #904 opened 22 days ago by yishaigalatzer
  1

• RuntimeError: Bad StatusOr access: INVALID_ARGUMENT: PJRT_Client_Create: error condition nullptr != (args)->client->Error(): Init: error condition !(num_devices > 0):

  #902 opened 24 days ago by PrateekAg1511
  3

• BERT model implemented usiing TransformerEncoder returns all NaNs when running it torch==1.13.1

  #903 opened 23 days ago by sgaseretto
  1

• Multiple models on torchserve

  #898 opened 23 days ago by brunonishimoto
  5

• Internal tensorizer error on RWKV model

  #878 opened 2 months ago by pm-mck
  4

• JAX inference (Beta)

  #900 opened a month ago by eshalakhotia
  0

• Support for falcon 2 / falcon 2 vlm

  #899 opened a month ago by renos
  1

• Error "ImportError: cannot import name 'packaging' from 'pkg_resources'" when using latest setuptools version 70

  #893 opened a month ago by jeffhataws
  5

• Compilation failed for llama3-70B model - Estimated peak HBM usage (22.839451) exceeds 16GB. Neff won't be able to load on chip

  #884 opened 2 months ago by ak-org
  3

• Running Llama3 Returns Tensor Allocate Status 2

  #891 opened a month ago by pedrohernandezgeladocma
  3

• NEFF Unable to open: kelf-b.json - 2 when loading in a model traced on 4 NeuronCores

  #894 opened a month ago by Bartosz-G
  1

• k8s-neuron-device-plugin - LICENSE and Source

  #895 opened a month ago by adammw
  0

• Failing to load a traced model

  #892 opened a month ago by brunonishimoto
  3

• Dynamic batching in inference doesn't work when embedding layers are included and input is two tensors

  #862 opened a month ago by fabiozappo
  2

• Need to use swap memory for loading (sdxl turbo) model, But I can't set it in sagemaker

  #858 opened 3 months ago by Suprhimp
  3

• Error when using torch.block_diag method

  #855 opened a month ago by joelamzn
  2

• Is F.interpolate support on neuronx-cc due to Unsupported CustomCall target: ResizeBilinear

  #889 opened a month ago by takipipo
  1

• uninterruptible containers when neurons attached to it

  #887 opened a month ago by oOraph
  6

• Doc issue: Inf2 data types has bad link for int8

  #890 opened a month ago by jimburtoft
  1

• When running BERT pretraining tutorial, seeing errors ``RuntimeError: unable to open file <> in read-only mode: No such file or directory ``

  #888 opened a month ago by jeffhataws
  0

• `neuron_parallel_compile` fails when an non utf-8 character

  #886 opened 2 months ago by michaelbenayoun
  1

• Converting TF2 MaskRCNN model to NeuronX on Inf2 instance fails

  #876 opened 2 months ago by saintarian
  2

• Internal tensorizer error when trying to compile and train a simple CNN

  #881 opened 2 months ago by sgaseretto
  3

• Quantized `mistral` model on Inf2 with Neuron?

  #856 opened 3 months ago by jpaye
  4

• Error: MPMD detected but reload is not supported yet

  #882 opened 2 months ago by wfckl789
  1

• Internal Compiler error when compiling a model

  #863 opened 2 months ago by alexandrekm
  4

• Issue while installing torch-neuronx==2.1.*

  #875 opened 3 months ago by bindu-0107
  3

• LLM engine not using Neuron device with continuous batching using vLLM

  #873 opened 3 months ago by ashwinikumar-sa
  2

• compiler_args not passed in for torch_neuronx.trace

  #865 opened 3 months ago by brianloyal
  3

• Failure on neuron-cc compilation when a nn model is moved to Neuron device

  #872 opened 3 months ago by wfckl789
  2

• torch.argsort crashes when tensor is on Neuron device

  #868 opened 3 months ago by evellasques
  1

• tensor copy out too slow (XLATensor::ToTensor)

  #860 opened 3 months ago by aws-liuliiily
  0

• Bug in `configure_pjrt_environment`

  #869 opened 3 months ago by michaelbenayoun
  1

• Error: "Backward sending grads, but get None"

  #864 opened 3 months ago by wfckl789
  1

• [HF][Optimum] Compiling unet in stable diffusion XL pipeline failed since Neuron SDK 2.18

  #859 opened 3 months ago by JingyaHuang
  8

• Embedding layer of ViT not supported with dynamic batch size

  #861 opened 3 months ago by fabiozappo
  1