grf53 commented on PR #18578: URL: https://github.com/apache/tvm/pull/18578#issuecomment-3698495430
@giterator @MasterJH5574 (I mentioned you because you seem to be related to this part.) Hello, I'd like to confirm your awareness of this issue. This issue is considered a critical one, as it blocks compilation of LLM models with the latest version of TVM, but it appears to have remained unfixed for a week or more. I'm unable to build the lib for the LLM model using tvm and mlc-llm (`mlc-llm-nightly-cu130`, `mlc-ai-nightly-cu130` or sth else.) installed with the latest whl files from https://mlc.ai/wheels, due to the same issue mentioned in this PR. I don't know if this will help: it seems to be happening within the last two months or so, as it seems to be working fine based on a version committed two months ago. -- 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]
