google / jetstream-pytorch

PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"
Apache License 2.0
32 stars 14 forks source link

Update README.md #87

Closed JackCaoG closed 3 months ago

JackCaoG commented 3 months ago

run_server takes model instead of model_name

JackCaoG commented 3 months ago

I don't have write access, can someone merget his pr for me? Thanks.

bhavya01 commented 3 months ago

Forgot to notice before. Can we also mention that this is for llama2 and also add the sharding_config flag?

JackCaoG commented 3 months ago

Updated