forked from pool/python-onnx
Guillaume GARDET
33748538ef
- update to 1.16.0
* Update to support int4 and uint4:
+ Cast, CastLike, Constant, ConstantOfShape, Identity, If,
Loop, Reshape, Scan, Shape, Size
* Update to support float8e4m3fnuz, float8e5m2, float8e5m2fnuz,
int4 and uint4:
+ Flatten, Pad, Squeeze, Transpose, Unsqueeze
* Support blocked quantization. Support int4, uint4, int16, and uint16:
+ DequantizeLinear, QuantizeLinear,
* Support bfloat16 and float16 scales. Support float8e4m3fn,
float8e4m3fnuz, float8e5m2, float8e5m2fnuz quantized tensors:
+ QLinearMatMul,
* Add stash_type attribute and change input shape of scale and
bias from (G) to (C) for GroupNormalization
* ai.onnx.ml Opset 4
* Addeded new operator TreeEnsemble
* IR Version 10
+ Added support for UINT4, INT4 types
+ GraphProto, FunctionProto, NodeProto, TensorProto added
metadata_props field
+ FunctionProto added value_info field
+ FunctionProto and NodeProto added overload field to support
overloaded functions.
- Security Updates
* Fix path sanitization bypass leading to arbitrary read
(CVE-2024-27318)
* Fix Out of bounds read due to lack of string termination in
assert (CVE-2024-27319)
- Several Bug fixes and infrastructure improvements
- removed python39 support
OBS-URL: https://build.opensuse.org/request/show/1162838
OBS-URL: https://build.opensuse.org/package/show/science:machinelearning/python-onnx?expand=0&rev=43