Jin Chi He
Jin Chi He
/question Hello, this is a question, is that kaniko support build multi-arch images? how to build multi-arch image using kaniko? Any docs or best practice? Thanks a lot! Refer to...
`containerregistry v0` in Pypi is created by @mattmoor and `containerregistry-ccwienk` is created by @ccwienk, seem the `containerregistry v0` is not updated, and `containerregistry-ccwienk` now v0.2.3. Any plan to update `containerregistry`...
/kind feature **Describe the solution you'd like** Since the kfserving will be intergrated by https://github.com/kubeflow/fairing/pull/299. But the testing platform is not installed kfserving, so the cases will be failed. Firstly...
/kind feature **Describe the solution you'd like** There is a folder `containerregistry` under fairing, and the package is installed by fairing (`pip install fairing`), in fact, the `containerregistry` is from...
/kind bug **What steps did you take and what happened:** The case `test_storage_account_creation` failed in presummit integration ``` Step #2: ________________________ test_storage_account_creation _________________________ Step #2: [gw0] linux -- Python 3.7.4...
/kind bug **What steps did you take and what happened:** While I execute the notebook using `papermill`, the below problem happened. ``` (python36) [root@jinchi1 testing]# python execute_notebook.py /tmp/tmpu433eq_r Executing: 48%|████████████████████████████████████████████▎...
``` Step #2: ________________________________ test_lightgbm _________________________________ Step #2: [gw6] linux -- Python 3.7.5 /usr/local/bin/python Step #2: Step #2: def test_lightgbm(): Step #2: file_dir = os.path.dirname(__file__) Step #2: notebook_rel_path = "../../../examples/lightgbm/distributed-training.ipynb"...
/kind bug **What steps did you take and what happened:** Hello, when I trying to setting up metadata, `make build` finished, and `make test` all passed. But hit the below...
/kind feature **Describe the solution you'd like** Suggest supportting [vLLM](https://github.com/vllm-project/vllm) or [deepspeed-fastgen](https://github.com/microsoft/DeepSpeed/tree/master/blogs/deepspeed-fastgen) for LLM inference, that's hot for inference projects now. **Anything else you would like to add:** fastest LLM...
/kind feature **Describe the solution you'd like** DeepSpeed-Inference introduces several features to efficiently serve transformer-based PyTorch models. It supports model parallelism (MP) to fit large models that would otherwise not...