onnxruntime/onnxruntime
Patrice Vignola 61e07a46e1
[DML EP] Support split hidden size for RotaryEmbedding (#18852)
RotaryEmbedding now supports the `[batchSize, numHeads, sequenceLength,
headSize]` format for its input, which is used in Mistral.
2024-02-12 19:36:08 -08:00
..
contrib_ops Revert "Revert NeuralSpeed code for x64 MatMulNBits (#19382)" (#19474) 2024-02-09 09:24:54 -08:00
core [DML EP] Support split hidden size for RotaryEmbedding (#18852) 2024-02-12 19:36:08 -08:00
python add arm64 bfloat16 fastmath mode option for transformers benchmarking script (#19294) 2024-02-12 15:20:36 -08:00
test Add option to skip session run in perf_test tool (#19501) 2024-02-12 19:11:40 -08:00
tool/etw Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
wasm [js/webgpu] Support capture and replay for jsep (#18989) 2024-01-30 18:28:03 -08:00
__init__.py [ORT 1.17.0 release] Bump up version to 1.18.0 (#19170) 2024-01-17 11:18:32 -08:00
ReformatSource.ps1 Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
ReformatSourcePython.bat
VSCodeCoverage.runsettings