Hai Minh Nguyen
Hai Minh Nguyen
**Describe the bug** I deployed Label Studio on out internal K8s cluster using the official helm-chart (version 14.0.10). When I sync data storage (a minio cluster on the same k8s...
**Describe the bug** I set my serving runtime to have a minimum replicas of 3. But my inference service will not be scheduled in the third serving runtime server. The...
**Is your feature request related to a problem? If so, please describe.** **Context**: - I am deploying multiple Triton Inference Servers on k8s, each is an API (for example Document...
### Checks - [X] I have searched the [existing issues](https://github.com/deployKF/deployKF). - [X] This issue is NOT security related. (Please [disclose responsibly](https://github.com/deployKF/deployKF/security)) - [X] This issue is NOT specific to the...
### Checks - [X] I have searched the [existing issues](https://github.com/deployKF/deployKF). - [X] This issue is NOT security related. (Please [disclose responsibly](https://github.com/deployKF/deployKF/security)) - [X] This issue is NOT specific to the...
### Checks - [X] I have searched the [existing issues](https://github.com/deployKF/deployKF). - [X] This issue is NOT security related. (Please [disclose responsibly](https://github.com/deployKF/deployKF/security)) - [X] This issue is NOT specific to the...
### Environment * KFP SDK version: 2.8.0 ### Steps to reproduce ``` @pipeline(name='test_cpu_request'): def pipeline(cpu_request: str): task.set_cpu_request(cpu_request) ``` Error: ``` Traceback (most recent call last): File "pipeline.py", line 13, in...
# Context I am learning how the auto scaling of the model mesh works. I found this piece of [docs](https://github.com/kserve/modelmesh/tree/3a4445030d1ffbf1c1b35a37a5cf4bac3bbb30de/docs/configuration): ``` Models will scale to two copies if they have...
### Checks - [X] I have searched the [existing issues](https://github.com/deployKF/deployKF). - [X] This request is NOT specific to the CLI. (Please open a [CLI issue](https://github.com/deployKF/cli/issues)) ### Motivation I can see...
Hi, the Triton's [model_config.proto](https://github.com/kserve/modelmesh-runtime-adapter/blob/main/internal/proto/triton/model_config.proto) has not been update for 3 years. Therefore, it is missing many of the new Triton configurations. I created a [PR](https://github.com/kserve/modelmesh-runtime-adapter/pull/92) to update the model_config.proto to...