jrmccluskey commented on PR #41005: URL: https://github.com/apache/beam/pull/41005#issuecomment-6827380350
Yep my own exploration around updating vLLM to silence some dependabot alerts ran into the same issue around triton and torch. The hard caps we have to enforce are very annoying. @damccorm do you have any thoughts on what we need to include in the GPU containers? -- 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]
