Tianqi Chen
Tianqi Chen
@dwwu please cross check your tvm installation, and follow instruction to rebuild tvm unity
try out https://webllm.mlc.ai/, which already works in web
OK I get what you mean. As of now the rust SDK does not yet compiles to wasm/webgpu. It can be used to interact with the chat module in other...
closing as the original question was answered and there is no extra actionable items
We removed rust part for now because we are transitioning to the new MLCEngine backend and the original rust was for legacy ChatModule, @LeshengJin is looking into adding support Likely...
This is a good first step towards embedding support through python-level API, would be great to also think about what does it take to bring it as part of the...
please fix the jenkins here
https://llm.mlc.ai/docs/deploy/ios.html# this should be fixed by latest ios sdk
Thanks for the suggestion, we are still focusing on a major refactoring push to stablize the universal deployment use-case so cannot quickly add new format support as of now. This...
right, the loader and quantization combined would be effectively a converter like you mentioned