MasterJH5574 opened a new issue, #20388: URL: https://github.com/apache/tvm/issues/20388
Dear TVM community, This is a call for vote to release Apache TVM version v0.27.0. Release highlights: * TIRx/CUDA: a table-driven PTX dialect with expanded instruction coverage, register and cluster launch controls, and additional tcgen05 support. * IR and arithmetic: shared expression traversal and mutation infrastructure, first-class tuple expressions, and BigInt-backed integer immediates and arithmetic coefficients. * Relax frontends: broader ONNX and PyTorch operator support and correctness fixes, plus StableHLO shape operations and quantized SSD inference fixes in TFLite. * Runtime and backends: shared-KV attention with configurable sliding windows, KV-cache checkpoint primitives, TensorRT engine construction during code generation, and LLVM 23 compatibility. * WebGPU/WASM: fewer tensor-cache and upload copies, per-parameter cache encoding, in-place BF16 decoding, and buffer-access and allocation fixes. Link to release candidate: https://dist.apache.org/repos/dist/dev/tvm/tvm-v0.27.0-rc0/ Link to GitHub pre-release page (full release notes): https://github.com/apache/tvm/releases/tag/v0.27.0.rc0 Everyone is welcomed to vote. Please vote by replying to this thread explicitly. According to release procedure, [for the dev@ vote, there must be at least 3 binding +1 votes and more +1 votes than -1 votes](https://tvm.apache.org/docs/contribute/release_process.html?highlight=release#call-a-vote-on-the-release-candidate). +1 = approve +0 = no opinion -1 = disapprove (provide reason) NOTE: this thread is being mirrored in dev@ This vote will remain open for at least 72 hours. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
