| 12412035 |
Token packing for sequence models |
Andy Wagner, Marc Tremblay |
2025-09-09 |
| 12380332 |
Forcing weights of transformer model layers |
Andy Wagner, Marc Tremblay |
2025-08-05 |
| 12182716 |
Compressing and decompressing data for language models |
Andy Wagner, Marc Tremblay |
2024-12-31 |
| 11954448 |
Determining position values for transformer models |
Andy Wagner, Marc Tremblay |
2024-04-09 |
| 11928429 |
Token packing for sequence models |
Andy Wagner, Marc Tremblay |
2024-03-12 |
| 11893469 |
Position masking for transformer models |
Andy Wagner, Marc Tremblay |
2024-02-06 |
| 11886983 |
Reducing hardware resource utilization for residual neural networks |
Andy Wagner, Marc Tremblay |
2024-01-30 |
| 11663444 |
Pipelined neural network processing with continuous and asynchronous updates |
Andy Wagner, Saurabh M. Kulkarni, Marc Tremblay, Sujeeth S. Bharadwaj |
2023-05-30 |
| 11610120 |
Systems and methods for training a neural network |
Andy Wagner, Marc Tremblay |
2023-03-21 |
| 11544537 |
Token-position handling for sequence based neural networks |
Andrew Wagner, Sujeeth S. Bharadwaj, Marc Tremblay, Saurabh M. Kulkarni |
2023-01-03 |
| 11537890 |
Compressing weights for distributed neural networks |
Andy Wagner, Marc Tremblay |
2022-12-27 |
| 11520592 |
Executing large artificial intelligence models on memory-constrained devices |
Bharadwaj Pudipeddi, Marc Tremblay, Gautham Popuri, Layali Rashid, Mohit Mittal +1 more |
2022-12-06 |
| 11475303 |
Spread neural networks |
Andrew Wagner, Sujeeth S. Bharadwaj, Saurabh M. Kulkarni, Marc Tremblay |
2022-10-18 |
| 11449752 |
System and method for gradient accumulation with free momentum |
Andrew Wagner, Marc Tremblay, Saurabh M. Kulkarni, Sujeeth S. Bharadwaj |
2022-09-20 |
