tvm
tvm copied to clipboard
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Bumps [certifi](https://github.com/certifi/python-certifi) from 2022.12.7 to 2024.7.4. Commits bd81538 2024.07.04 (#295) 06a2cbf Bump peter-evans/create-pull-request from 6.0.5 to 6.1.0 (#294) 13bba02 Bump actions/checkout from 4.1.6 to 4.1.7 (#293) e8abcd0 Bump pypa/gh-action-pypi-publish from...
Prior to this commit, TVMScript required the return value of a Relax to be specified outside of any `with R.dataflow()` blocks. This resulted in a common pattern, where the return...
If the loop domain depends on other loops, currently there is missing transformations in `CreatePrimFunc`, which lead to undefined variables in lowering. https://discuss.tvm.apache.org/t/compilation-error-for-adaptive-avg-pool2d-relax-op-in-mlc-llm/17784
### background I want to use vta in tvm I follow the tutorial from official website,set these open ``` # Whether to build fast VTA simulator driver set(USE_VTA_FSIM ON) #...
Hello, I was facing few time problems when TVM says about undefined error -14. But this error is described(https://streamhpc.com/blog/2013-04-28/opencl-error-codes/) as `CL_EXEC_STATUS_ERROR_FOR_EVENTS_IN_WAIT_LIST`. So I have added it. I think more error...
Dear TVM community, This is a call for vote to release Apache TVM version v0.18.0. for any edits you would like to see included in the release notes. Link to...
As per title.
Continuing on https://github.com/apache/tvm/pull/17433. The images changed are arm, cortexm, cpu, gpu, hexagon, riscv.
0.17.0 fails with GCC14 (on openSSUE Tumbleweed) with: `error: control reaches end of non-void function [-Werror=return-type]` ### Expected behavior Build should succeed with GCC14. ### Actual behavior Build fails with:...
Please review the fix: It is a unique use-case to check the default target(LLVM), though TVM is built with BYOC(MRVL-ON) The config of Codegen(BYOC) contains default values for configuration/optons, it...