-
RFC PR: https://github.com/apache/tvm-rfcs/pull/37
### This issue is to track progress for the Arm(R) Ethos(TM)-U Cascading Scheduler
- [x] P1. Add analysis infrastructure for data dependencies be…
-
These tests were found to be flaky (intermittently failing on `main` or failed in a PR with unrelated changes). See [the docs](https://github.com/apache/tvm/blob/main/docs/contribute/ci.rst#handling-f…
-
Working on this PR: https://github.com/apache/tvm/pull/11809
This will increase the workload on ci_qemu and it has timeout issue. So it's time to shard this image like others.
cc @Mousius @areusch…
-
https://tvm.apache.org/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
https://tvm.apache.org/docs/how_to/deploy_models/deploy_sparse.html
-
On a recent PR that added a few extra tests to Relay, we discovered that pytest was running over the 4GB RAM limit on the x386 CI job. We fixed this by reducing the memory use of the failing test ~10%…
-
Seems to me the multi-input head and the constant nodes get unconnected quite often (almost always).
On the one hand, it helps us get new bugs on frameworks that poorly support this unreal models;
…
-
Creating this issue as a reminder that tests in the TFLite frontend seem to be missing `_test_tflite2_quantized_depthwise_convolution`, which shows lack of coverage for that particular operator.
-
Hi,
I used a variant of pre-trained Alexnet model with a subset of cifar100 dataset. I am getting lower accuracy with TVM compared to PyTorch. I made two modifications to the original model. I chan…
-
The serialization/deserialization of Relax executable seems to have a bug in presence of symbolic shapes.
### Repro Unit Test
Serializing and deserializing the executable in the [unit test](http…
-
Every time you build a relay module using AOT codegen, the order in C file changes. This is specially important for microTVM because it makes debugging difficult since debug pointers change per execu…