mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-29 20:14:01 +00:00
Fix longformer parity and perf regression (#6760) … Adding fp16 support for Einsum Cuda kernel (#6775) … Update DirectML 1.4.1 to 1.4.2 for ORT 1.7 (#6780) … Fix regression in constant folding optimizer (#6795) Update transformers benchmark for transformers 4.3.* and ORT 1.7 (#6796) … Make keepdims to its default value when adding ReduceMin/ReduceMax fo (#6788)… … fix issues caused by quantize/calibrate changes (#6802) 6735 and 6728 already in release branch Co-authored-by: Tianlei Wu <tlwu@microsoft.com> Co-authored-by: Ye Wang <52801275+wangyems@users.noreply.github.com> Co-authored-by: Ori Levari <orlevari@microsoft.com> Co-authored-by: Hariharan Seshadri <shariharan91@gmail.com> Co-authored-by: Chi Lo <54722500+chilo-ms@users.noreply.github.com> Co-authored-by: stevenlix <38092805+stevenlix@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| github | ||
| __init__.py | ||
| amd_hipify.py | ||
| build.py | ||
| clean_docker_image_cache.py | ||
| coverage.py | ||
| exclude_unused_ops_and_types.py | ||
| gen_def.py | ||
| get_docker_image.py | ||
| logger.py | ||
| op_registration_utils.py | ||
| op_registration_validator.py | ||