tvm-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Tianqi Chen <>
Subject Re: [dmlc/tvm] [RFC][Quantization] Support quantized models from TensorflowLite (#2351)
Date Thu, 30 May 2019 00:19:27 GMT
Here are some points to discuss:

- namespace for the tflite quantize style dialect
- List of ops that might need tvm's compute declaration
- set of possible passes that lower the rest into the core ops

Some of the discussions involve fusion, and that is something where TVM might be able to help.
For example, in the current symmetric scheme, clip,  relu6, and subsequent downcasting ops
are automatically fused into the conv2d ops. While the conv2d op can simply just output int32(because
followup ops will get fused).

I agree that we could try to get something minimum that is working, then start thinking about
possible rewriting rules to get to some useful patterns if we decide that manual intervention
is necessary.

Ideally, we should have a generic schedule template that works for any fused patterns, just
as those in the current symmetric version, so we do not need to have all the different variants
of fused conv2d ops

also cc @vinx13 @ZihengJiang 

You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
  • Unnamed multipart/alternative (inline, 7-Bit, 0 bytes)
View raw message