fixed CUBLAS bindings and hardcoded LLAMA_MAX_DEVICES

sobelio / llm-chain

`llm-chain` is a powerful rust crate for building chains in large language models allowing you to summarise text and complete complex tasks

https://llm-chain.xyz

MIT License

1.3k stars 128 forks source link

Closed andychenbruce closed 1 year ago

andychenbruce commented 1 year ago

Bindings didn't work right when the cuda feature was enabled.

Juzov commented 1 year ago

Thanks for you pr, I can't test this as I don't have a cuda gpu, so we'll just have to base it that it works for you