tvm
tvm copied to clipboard
[Tracking Issue] TFLite operator support
In https://github.com/apache/tvm/issues/9187 we implemented quantised version of operators in TFLite frontend. Recently, I just noticed a few more operators (with varying priorities) that can be taken as beginner friendly tasks, for someone who's starting in TVM.
I'm creating this as a tracking issue to mark those operators that need to have quantization support implemented and tested:
- [x]
FLOOR_DIV
(#15724) - [x]
FLOOR_MOD
(#15733) - [x]
DIV
(#15768) - [x]
POW
(#15798) - [ ]
REVERSE_SEQUENCE
(#15915) - [x]
SQUARE
(#15914) - [x]
ELU
(#15821) - [ ]
LOCAL_RESPONSE_NORMALIZATION
(LRN) - [ ]
L2_NORMALIZATION
- [x]
MIRROR_PAD
(#16243) - [ ]
ARG_MIN
(#15922) - [x]
NOT_EQUAL
(#15769) - [x]
LESS
(#15746) - [x]
LESS_EQUAL
(#15790) - [x]
GREATER_EQUAL
(#15775)
For each operator above, there are actions to be taken:
- Remove the conditional block
if self.is_quantized(op): ...
- Implement unit tests
- ask any committer in the project to update this issue, reflecting the PR to support the operators on the list above
https://github.com/apache/tvm/pull/9165 can be used as an example.
In case you're interested, a good starting point is the TFLite frontend: https://github.com/apache/tvm/blob/bee073b0c8e8625216184a2dbb0204c0a376fc26/python/tvm/relay/frontend/tflite.py#L78-L185