Liang-Chi Hsieh

Incorrect mapping from proto message to Rust Struct

1

For example, I have two proto files, expr.proto and operator.proto. ```proto // expr.proto package proto.expression; message Expr { ... } ``` ```proto package proto.operator; import "proto/expr.proto"; message Projection { repeated...

Does prost generate accessor for oneof field? For a field, prost will generate the accessor `set_{fieldname}`, but seems for a oneof field, there is no such accessor. Do I use...

As I tried to use the influxdb dashboard, seems that the influx npm module it installed is too old. This patch upgrades the influx npm module to at least 5.0.0...

### What happened + What you expected to happen Due to the issue #43261, I currently can only use 1 cpu per worker (i.e., `resources_per_worker={"CPU": 1}`). The RayCluster has 6...

### What happened + What you expected to happen I use RayJob to submit a text ml job. I follow the doc https://docs.ray.io/en/latest/ray-core/scheduling/resources.html to specify cluster resource like cpu in...

computation performs slower than cpu version in benchmark

3

Hi, I'm running some benchmarks between the computation code from metal-rs and a cpu version. I basically benchmark the compute example which does `sum` operation and a cpu version which...

Add support of right join

2

It will be more convenient to have the support of right join.

Run rayllm frontend on head pod fails

1

I tried to run the rayllm frontend on the deployed rayllm head pod: ``` serve run rayllm.frontend.app:app --non-blocking ``` But got: ``` 2024-03-11 16:09:55,259 INFO scripts.py:438 -- Running import path:...

I've deployed rayllm on K8s with amazon--LightGPT model. I can query it from local using `curl`. But when I go to run `serve status` on the head pod, I got...

I'm following this instructions to deploy rayllm on K8s. In the step I updated, I don't see `aviary-serve-svc` but only `rayllm-serve-svc`. I created a port-forward with it and the following...