yelite opened a new pull request, #15064: URL: https://github.com/apache/tvm/pull/15064
This would be useful when creating multiple kv caches with the same shape. On A10G, compared to creating 64 kv caches separately in LLaMA from mlc-llm, doing a single allocation can save about 35 ms. @tqchen @junrushao -- 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]
