Skip to content

Issues: aws-neuron/transformers-neuronx

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

22 Open 50 Closed
22 Open 50 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Llama and Mistral model inputs change after using different computation
#104 opened Dec 20, 2024 by kahfizulkifli
6
Loading compiled fails: model_type=bert -> transformers being used in compiled config.
#102 opened Dec 2, 2024 by michaelfeil
1
Neuron model NEFFs are dependent on the python path
#99 opened Oct 7, 2024 by dacorvo
2
Gibberish output for princeton-nlp/Sheared-LLaMA-1.3B with continuous batching
#94 opened Jul 15, 2024 by pinak-p
2
Not able to load llama 3 70b on inf2.24xlarge instance
#92 opened Jul 10, 2024 by sangraamp
6
Any plan to support Qwen-2 Model
#89 opened Jun 27, 2024 by mynewstart
1
llava support
#88 opened Jun 20, 2024 by sonic182
4
Latest changes introduced for continuous batching break Mixtral model bug Something isn't working
#84 opened Apr 15, 2024 by dacorvo
5
Add support for Baichuan-13B model
#83 opened Apr 9, 2024 by cszhz
Add support for gemma models
#82 opened Apr 2, 2024 by benglewis
1
Improve Neuron model loading time
#80 opened Mar 13, 2024 by dacorvo
4
Backward compatibility with saved llama 2 compiled artifacts enhancement New feature or request
#78 opened Jan 18, 2024 by dacorvo
1
User feedback when compiling and reloading a large model enhancement New feature or request
#76 opened Jan 17, 2024 by dacorvo
1
Support for MPT model
#74 opened Jan 11, 2024 by klutzDrawers
1
Infering logits from model.forward for the entire batch instead of the last forward's output. documentation Improvements or additions to documentation
#73 opened Jan 10, 2024 by michaelfeil
6
Generate Llama 2 from Embeddings
#72 opened Jan 8, 2024 by liechtym
5
Vicuna13B model support
#66 opened Dec 19, 2023 by petrovicu
1
Any solution to save the converted model? enhancement New feature or request
#29 opened Aug 14, 2023 by aliseyfi
3
Discrepancies Between GPU and Neuron-based Outputs for GPTJ Model on inf2.24xlarge
#28 opened Aug 13, 2023 by ho4040
2
Running GPT-NeoX on inf2.24xlarge kills kernel
#24 opened Jul 22, 2023 by aliseyfi
2
Support for Falcon models
#18 opened Jul 9, 2023 by user-10389
3
BART support
#11 opened Jun 23, 2023 by sinking-point
1
ProTip! Updated in the last three days: updated:>2024-12-22.