webmachinelearning/webnn Issues

Last updated Mar 9, 2026, 11:44:04 PM 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.

20 out-of-SLO untriaged issues

Untriaged

Try to triage issues within 7 days. [ More Info ]

Issue	Title	Within SLO	On maintainers' plates for	Time past SLO
#21	(Computer) network-related use cases	❌	6.7 years	6.7 years
#24	Backwards compatibility of the initial set of ops	❌	6.5 years	6.5 years
#165	Add models to the spec appendix	❌	4.8 years	4.8 years
#189	Request for BatchToSpaceND and SpaceToBatchND ops	❌	4.7 years	4.7 years
#252	Support for non-IEEE 754 float point types	❌	4.1 years	4.1 years
#374	Simplify `MLPool2dOptions` by removing the `outputSizes` option	❌	2.9 years	2.9 years
#537	Vision transformers	❌	2.1 years	2.1 years
#559	Control flow operations: if, while	❌	2.1 years	2.1 years
#759	MLOpSupportLimits should be opt-in with base functionality	❌	1.5 years	1.5 years
#766	Allow setting label for constant operand	❌	1.4 years	1.4 years
#867	May we update `reversed` options of `cumulativeSum` operation as `reverse`?	❌	9 months	8.8 months
#876	How to support explicit padding on TFLite backend	❌	7.1 months	6.9 months
#877	How to support edge padding mode on TFLite backend	❌	7.1 months	6.9 months
#878	How to support scatterElements on TFLite backend when indices operand is not constant	❌	7.1 months	6.9 months
#896	Add minimum data type set and rank range for input, constant, output and each operator into Spec	❌	4.4 months	4.1 months
#899	Idea for Discussion: Incremental Batch Learning and Fine-tuning	❌	4.3 months	4.1 months
#900	CPU fallback hint	❌	4.3 months	4 months
#903	Expand the expand operator to support blockwise broadcasting	❌	3.9 months	3.7 months
#904	2D, or not 2D, that is the question	❌	3.9 months	3.7 months
#919	Creating a context should be done using finer-grained in-parallel steps	❌	2.9 weeks	1.9 weeks