DustinBrett opened a new pull request, #14722: URL: https://github.com/apache/tvm/pull/14722
Based on a [comment](https://github.com/mlc-ai/web-llm/issues/57#issuecomment-1518639252) from @tqchen I've gone ahead and made a PR for my [suggestion/question](https://github.com/mlc-ai/web-llm/issues/57) of caching `ndarray-cache.json` before caching the shards. From my point of view this change means subsequent loads will pull 100% from CacheStorage, avoiding any external requests. Also I think this might make more sense because if your `ndarrayCacheUrl` is not pinned to a specific commit then it could perhaps become out of sync with the cached shards. -- 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]
