Re: [I] [VOTE] Release Apache TVM v0.16.0.rc0 [tvm]

ysh329 commented on issue #16912: URL: https://github.com/apache/tvm/issues/16912#issuecomment-2078718265 Hi all, please vote. cc @Lunderberg @Hzfengsy @vinx13 @junrushao @tqchen -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHu

Re: [PR] Enable gemv schedule for adreno [tvm]

krishnaraj36 commented on PR #16932: URL: https://github.com/apache/tvm/pull/16932#issuecomment-2078685568 @srkreddy1238 @tqchen : Can you please take a look in this PR -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use t

(tvm) branch nightly updated (4f8c03fad3 -> 51cfb70f86)

This is an automated email from the ASF dual-hosted git repository. github-bot pushed a change to branch nightly in repository https://gitbox.apache.org/repos/asf/tvm.git from 4f8c03fad3 [TVMScript] Support `T.launch_thread` with i64 dtype (#16916) add 39f2482580 [Fix] Fix SSA conversi

(tvm) branch main updated: [Fix][Dlight] Fix GeneralReduction for log-sum-exp (#16923)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git The following commit(s) were added to refs/heads/main by this push: new 51cfb70f86 [Fix][Dlight] Fix GeneralReduction for log-s

Re: [PR] [Fix][Dlight] Fix GeneralReduction for log-sum-exp [tvm]

tqchen merged PR #16923: URL: https://github.com/apache/tvm/pull/16923 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or

[PR] [CI] Use LLVM17 for tests on `ci_cpu` [tvm]

lhutton1 opened a new pull request, #16931: URL: https://github.com/apache/tvm/pull/16931 Changes the config script to build TVM with LLVM17. This enables tests for #16921. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[PR] [UnitTest] Use pytest's scope='session' for tvm.testing.parameter [tvm]

Lunderberg opened a new pull request, #16930: URL: https://github.com/apache/tvm/pull/16930 Prior to this commit, the `tvm.testing.parameter` utility defined a fixture with the default `scope="function"`. However, this prevents use of these parameters as arguments for other fixtures that a

Re: [PR] [Runtime] Allow inspection of function names from a compiled .so [tvm]

Lunderberg commented on PR #16836: URL: https://github.com/apache/tvm/pull/16836#issuecomment-2077686494 Looks like the re-implemented version has trouble with RPC devices and with microtvm runtime. In order to compile the metadata function, I needed to add the ability to return a `tir::St

[I] [Bug] Missing key in Vitis Ai docker demo [tvm]

Zaptos27 opened a new issue, #16928: URL: https://github.com/apache/tvm/issues/16928 ### Expected behavior That the docker can run without issue ### Actual behavior When I try to run the command ./docker/build.sh demo_vitis_ai bash, from the guide I get an error 3/21, RUN apt-ge

(tvm) branch main updated: [Fix] Fix SSA conversion for SizeVar retention (#16924)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git The following commit(s) were added to refs/heads/main by this push: new 39f2482580 [Fix] Fix SSA conversion for SizeVar retenti

Re: [PR] [Fix] Fix SSA conversion for SizeVar retention [tvm]

tqchen merged PR #16924: URL: https://github.com/apache/tvm/pull/16924 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or

Re: [PR] [SCRIPT][ADRENO] Fix in build config for adreno [tvm]

krishnaraj36 commented on PR #16927: URL: https://github.com/apache/tvm/pull/16927#issuecomment-2076852242 @srkreddy1238 : Can you please take a look in this PR. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL

[PR] [SCRIPT][ADRENO] Fix in build config for adreno [tvm]

krishnaraj36 opened a new pull request, #16927: URL: https://github.com/apache/tvm/pull/16927 1. Enable CXX environment setting for empty tvm subgraph. 2. Enable clml profiling and tuning in rpc environment 3. Enable Opencl when CLML build. -- This is an automated message from the

[PR] [TIR] Use enable_check in cache_read and add some boundary check [tvm]

qsqqsqqsq-intellif opened a new pull request, #16926: URL: https://github.com/apache/tvm/pull/16926 1. Do not check region cover for cache_read and cache_inline when schedule enable_check set to false. We don't need region cover check in some case. 2. Add some boundary check for ProducerC

[I] [Bug] run tests/python/relax/test_codegen_tensorrt.py coredump [tvm]

sky-fun opened a new issue, #16925: URL: https://github.com/apache/tvm/issues/16925 ### Environment ubuntu 18.04 llvm 13.0.1 cuda 11.7 TensorRT-8.4.1.5 python3.8.2 ### Steps to reproduce 1.build tvm with USE_CUDA ON、 USE_RELAY_DEBUG ON、 USE_TENSORRT_CODEGE