tvm
tvm copied to clipboard
apache
Open deep learning compiler stack for cpu, gpu and specialized accelerators
- [x] S0. Reason: [Introduce CSI-NN2 Compute Library into TVM to accelerate the inference performance of RISC-V CPU with Vector Extension](https://github.com/apache/tvm-rfcs/pull/75) - [x] S1. Tag of nightly build: TAG: [20220713-060117-ca88c522f](https://hub.docker.com/layers/ci_qemu/tlcpackstaging/ci_qemu/20220713-060117-ca88c522f/images/sha256-2677d128446861d93412b7a9bb631eccb8878fc9801a546d459df2bcaf105002?context=explore)...
Is there a way to verify that a PR hasn't resulted in an increased number of skipped tests? The "Tests" link in the Jenkins report shows skipped tests, but it...
[Runtime] Add runtime.contrib.set_custom_cpu_allocator to use custom memalign() and free() functions
This PR adds a new function runtime.contrib.set_custom_cpu_allocator to the registry which can be used to override the memalign() and free() functions used by CPUDeviceAPI. Upstream original [PR](https://github.com/neo-ai/tvm/pull/141) by @trevor-m ....
The main idea is to construct some handshake mechanism which can help to check that TVM executor obtained from pre-compiled libraries and other files is corresponded to given model. There...
- [ ] S0. Reason: (https://github.com/apache/tvm/pull/12030) - [ ] S1. Tag of nightly build: TAG. Docker hub: Don't see it corresponding to following commit in here: https://hub.docker.com/r/tlcpack/ci-cpu - [ ]...
I am using M1 mac to tune onnx resnet50 using the code from TVM tutorial. And I met problems both with autoscheduler and without it. ### Expected behavior It should...
* What this PR do: This pull request is related to issue #12009 . 1. I upgrade custom callback function type to xgboost latest version callback.TrainingCallBack function. 2. Because xgboost.cv()...
we had multiple instances where code changes resulted in skipping tests in the CI unintentionally. It would be great if we can have a tool which keeps track of the...
### Expected behavior What you were expecting Set USE_DNNL ON or OFF should not impact document processing ### Actual behavior What actually happened Set USE_DNNL ON then run "docker/bash.sh --env...
Repro: ``` # try to run linting locally on ubuntu python tests/scripts/ci.py lint ``` Stack trace: ``` Linting the Python code with flake8... + tests/lint/flake8.sh ./_xxx/xxx.py:93:22: E999 SyntaxError: invalid syntax...
