webmachinelearning/webnn Issues

Last updated Apr 27, 2026, 8:14:11 AM UTC.

This repository doesn't have the Priority: Eventually label that's used to mark an issue as triaged without giving it an SLO. Until that's added, this summary uses heuristics to guess if each issue has been triaged.

Untriaged

Try to triage issues within . [ More Info ]

Issue Title Within SLO On maintainers' plates for Time left Time past SLO
#21 (Computer) network-related use cases ❌
#24 Backwards compatibility of the initial set of ops ❌
#165 Add models to the spec appendix ❌
#189 Request for BatchToSpaceND and SpaceToBatchND ops ❌
#252 Support for non-IEEE 754 float point types ❌
#374 Simplify `MLPool2dOptions` by removing the `outputSizes` option ❌
#537 Vision transformers ❌
#559 Control flow operations: if, while ❌
#759 MLOpSupportLimits should be opt-in with base functionality ❌
#766 Allow setting label for constant operand ❌
#867 May we update `reversed` options of `cumulativeSum` operation as `reverse`? ❌
#876 How to support explicit padding on TFLite backend ❌
#877 How to support edge padding mode on TFLite backend ❌
#878 How to support scatterElements on TFLite backend when indices operand is not constant ❌
#896 Add minimum data type set and rank range for input, constant, output and each operator into Spec ❌
#899 Idea for Discussion: Incremental Batch Learning and Fine-tuning ❌
#900 CPU fallback hint ❌
#903 Expand the expand operator to support blockwise broadcasting ❌
#919 Creating a context should be done using finer-grained in-parallel steps ❌
#927 Security considerations refresh ❌
#929 RFE: Add batching support (N-D tensors) to the gemm operator ✔
#930 RFE: Add support for more floating point low-precision ML data types (`bfloat16`, `fp8`, `nvfp4`) ✔

Agenda

Try to maintain fewer than 25 agenda items and discuss issues on the agenda within . [ More Info ] [ See these issues on Github ]

Issue Title Within SLO On the agenda for Time left Time past SLO
#883 Support flexible input sizes ✔