QNN LPAI API Revision History

QNN LPAI API Version

Introduced in QNN SDK Version

Model Builder Version

Description

2.22.0

2.39.0

5.12.0

  • Add core selection config option

  • Support multi-type attributes

  • enable dspqueue for enpuV6 and enpuV5_1

2.21.0

2.38.0

5.11.2d1a28fc

  • Profiling improvements

  • PSRAM memory support

  • Support Async Execution

2.20.0

2.37.0

5.10.8421ef45

  • Add ubuf config option

  • Improvements on profiling

2.19.0

2.36.0

5.9.0c847578

  • LPAI BE adapted to work with 5.9 enpu components

  • More profiling improvements

  • Reset Call handling improvements

  • Added OP support: RmsNorm, Buffer Op Padding Param

2.18.0

2.35.0

5.8.35a52877

  • LPAI BE adapted to work with 5.8 enpu components

  • More profiling improvements

  • Added OP support: StatelessLSTM/GRU

2.17.0

2.34.0

5.7.9931d1e5

  • Simplified Lpai BE library names

  • LPAI Documentation improvements

  • enpu compile,execute, simulator libraries update

  • LPAI BE dapted to work with 5.7 enpu components update

  • More profiling improvements

  • Added OP support:BatchToSpace,SpaceToBatch,DepthToSpace,SpaceToDepth,Quantize,Dequantize

2.16.0

2.32.0

5.6.057f0428

  • Add device discovery mechanism across different LPAI Supported HW

  • Add support for LPAI graph early termination

  • Fix runtime stability issues

  • Improved Profiling information

  • Added OP support: Channel_Shuffle

2.15.0

2.31.0

5.5.addf3789

  • Add Compiler + Sim for x86 Windows

  • Fix fastRPC bugs for hex79,hex81

  • Documentation

  • mem Register/deRegister

2.14.0

2.30.0

5.4.ad7bd0ed

  • Add Support for Backend Custom properties

2.13.1

2.29.0

4.14.f7310daf

  • Add QNN LPAI island interface

  • Add model preparation and simulation support on x86 Windows platform

2.13.0

2.28.0

4.13.efc48af1

  • Align QNN LPAI config file defaults

  • Runtime check for compiled LPAI models older than v4.6, no longer supported

  • Prepare for LPAI Runtime Island Support

2.12.0

2.27.0

4.12.5bf898df

  • Add profiling support: graph execute time

  • Bug fix for unsupported float tensor

  • Bug fix for reset tensors as input

2.11.0

2.26.1

4.11.7fa40f05

  • Op update: Add default support of antialias param for ResizeBilinear Op

2.11.0

2.25.1

4.11.7fa40f05

  • Ops updates and bug-fixes: Split,LSTM,GRU,Batchnorm,Conv,StridedSlice,ReduceProd

  • Add profiling support: per layer execution time, layer fusion info, layer linking info

2.10.0

2.24.1

4.10.68490b7c

  • Add Op support: Buffer (Framer)

  • PerLayer Profiling support via configs

  • Version Checks for LPAI Execute

  • Start support for lightweight internal aDSP build

  • Memory allocation for internal aDSP Execute

2.9.0

2.23.1

4.9.0xa3f3a016

  • Optimize memory planning

  • Fix memory leaks issue during model conversion

  • Add Op support: Power, Layernorm, Split

  • Fixed memory leak 32 properly if initialization is failed

  • Fixed stability issue related to multiple threads/processes

  • Add API profiler parameter

2.8.0

2.22.1

4.8.42ed4bf0-v79

  • Added: Runtime eNPU5 Support, x86 generation, x86 Simulator and ARM execution

2.7.1

2.20.1

3.17.4446b3115

  • Added: LPAI BE Adaptor getMap() APIs

2.7.0

2.18.1

3.17.4446b311

  • Added: Support to model visualizer, eNPU4 for linux_x86, windows,hexagonsim and adsp

  • Added: LPAI BE getSupportedOperations()

  • Fixes: TensorID duplicate errors during QNN change from tensor name to tensorID

  • Fixes: Sanitize quantizations with invalid parameters

2.6.0

2.17.1

3.16.ae82aa87

  • Fixes: Fix resize op to account for annotations on sizes tensor

  • Added: Support to multiple loaded HW compiler versions

2.5.0

2.14.1

3.14.827f8f95

  • Fixes: Fix resize op to account for annotations on sizes tensor

  • Fixes: Deconv2D segfault data size calculated from model builder is incorrect.

  • Fixes: Fix segfault in case of min/max with constant tensor.

  • Fixes: Expand tensor shape when rank is different.

2.4.0

2.13.1

3.12.a4c0bd91

  • Fixes: Proper bias alignment for gemm with square output

  • Fixes: Improve layernorm accuracy for small hidden_size

  • Added: Support to different permutations of 1d bias matmul.

  • Added: New memory planning compiler pipeline

2.3.0

2.12.1

3.10.e4d3cfa4

  • Fixes: per-channel quantization

2.2.0

2.11.1

3.8.74ea5d84

  • See op support updates

2.1.0

2.10.1

3.6.546129c7

  • Fixes: symmetric quantization and compression ratio calc

  • Added: support multiple nodes with same id, input name from onnx node for perlayer dump

2.0.0

2.9.1

  • Initial release