aws-neuron/aws-neuron-sdk
Powering AWS purpose-built machine learning chips. Blazing fast and cost effective, natively integrated into PyTorch and TensorFlow and integrated with your favorite AWS services
PythonNOASSERTION
Issues
- 3
- 2
AWS NeuronX sdk installation
#916 opened by Zkarape - 4
Bad image quality for Stable Diffusion 1.5 after applying the optimized attenstion score
#897 opened by JingyaHuang - 1
DataParallel Support on CRF inference
#914 opened by jyang-aws - 1
neuron-distributed for inference
#915 opened by sonic182 - 2
ECS inf1 neuron hook script fails
#911 opened by rantoniuk - 4
- 0
- 0
Issue on page /frameworks/torch/torch-neuronx/programming-guide/training/pytorch-neuron-programming-guide.html
#912 opened by yahavb - 2
- 5
- 0
support for aten::upsample_nearest3d
#908 opened by SimonRelu - 1
- 4
Input tensor is not an XLA tensor: CPUFloatType while using crf.decode function
#901 opened by PrateekAg1511 - 1
- 3
RuntimeError: Bad StatusOr access: INVALID_ARGUMENT: PJRT_Client_Create: error condition nullptr != (args)->client->Error(): Init: error condition !(num_devices > 0):
#902 opened by PrateekAg1511 - 1
BERT model implemented usiing TransformerEncoder returns all NaNs when running it torch==1.13.1
#903 opened by sgaseretto - 5
Multiple models on torchserve
#898 opened by brunonishimoto - 4
Internal tensorizer error on RWKV model
#878 opened by pm-mck - 0
JAX inference (Beta)
#900 opened by eshalakhotia - 1
Support for falcon 2 / falcon 2 vlm
#899 opened by renos - 5
Error "ImportError: cannot import name 'packaging' from 'pkg_resources'" when using latest setuptools version 70
#893 opened by jeffhataws - 3
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 by ak-org - 3
- 1
NEFF Unable to open: kelf-b.json - 2 when loading in a model traced on 4 NeuronCores
#894 opened by Bartosz-G - 0
k8s-neuron-device-plugin - LICENSE and Source
#895 opened by adammw - 3
Failing to load a traced model
#892 opened by brunonishimoto - 2
Dynamic batching in inference doesn't work when embedding layers are included and input is two tensors
#862 opened by fabiozappo - 3
Need to use swap memory for loading (sdxl turbo) model, But I can't set it in sagemaker
#858 opened by Suprhimp - 2
Error when using torch.block_diag method
#855 opened by joelamzn - 1
Is F.interpolate support on neuronx-cc due to Unsupported CustomCall target: ResizeBilinear
#889 opened by takipipo - 6
uninterruptible containers when neurons attached to it
#887 opened by oOraph - 1
Doc issue: Inf2 data types has bad link for int8
#890 opened by jimburtoft - 0
When running BERT pretraining tutorial, seeing errors ``RuntimeError: unable to open file <> in read-only mode: No such file or directory ``
#888 opened by jeffhataws - 1
- 2
- 3
- 4
Quantized `mistral` model on Inf2 with Neuron?
#856 opened by jpaye - 1
Error: MPMD detected but reload is not supported yet
#882 opened by wfckl789 - 4
Internal Compiler error when compiling a model
#863 opened by alexandrekm - 3
Issue while installing torch-neuronx==2.1.*
#875 opened by bindu-0107 - 2
LLM engine not using Neuron device with continuous batching using vLLM
#873 opened by ashwinikumar-sa - 3
- 2
- 1
- 0
tensor copy out too slow (XLATensor::ToTensor)
#860 opened by aws-liuliiily - 1
Bug in `configure_pjrt_environment`
#869 opened by michaelbenayoun - 1
Error: "Backward sending grads, but get None"
#864 opened by wfckl789 - 8
[HF][Optimum] Compiling unet in stable diffusion XL pipeline failed since Neuron SDK 2.18
#859 opened by JingyaHuang - 1