Carson Wang

Hi @LAITRUNGMINHDUC, did you start a Ray cluster on a Databricks Spark cluster and then want to use RayDP? RayDP is Spark on Ray so it makes it look like...

Thanks @ConeyLiu for the suggestion. Probably we can test multiple Ray versions in the test and make sure they can work.

hi @Writer-X, Thanks for the update!

This has been improved in RayDP 0.5.0. Please see https://github.com/oap-project/raydp/blob/master/doc/spark_on_ray.md#logging

You can use `raydp.init_spark(..., placement_group_strategy="SPREAD")` to spread the Spark executors to all nodes. Please see https://github.com/oap-project/raydp/blob/master/doc/spark_on_ray.md#placement-group

Hi @chenya-zhang , there is a plan to integrate RayDP with Gluten which offloads the sql operations to native engine such as Velox. For TPC-H or TPC-DS like benchmark, we...

Is ray-llm going to be deprecated and this example will be the recommended way to run vllm on Ray?