python-onnx/onnx-1.16.0.tar.gz at factory - python-onnx - openSUSE Gitea

rpm/python-onnx

SHA256

forked from pool/python-onnx

Files

Guillaume GARDET 33748538ef Accepting request 1162838 from home:mslacken:branches:science:machinelearning

- 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

2024-03-27 10:28:58 +00:00

4 lines

133 B

Plaintext

Raw Permalink Blame History

	`version https://git-lfs.github.com/spec/v1`
	`oid sha256:0ce153e26ce2c00afca01c331a447d86fbf21b166b640551fe04258b4acfc6a4`
	`size 12428161`