Ernest Wong
Ernest Wong
Populate contents for https://azure.github.io/azure-workload-identity: - [x] Introduction - [x] Installation - [x] Quick Start - [x] Concepts - [ ] Topics - [x] Mutating Admission Webhook - [x] Service Account...
/kind bug **What steps did you take and what happened:** [A clear and concise description of what the bug is.] example: https://prow.k8s.io/view/gs/kubernetes-jenkins/pr-logs/directory/pull-kubernetes-e2e-capz-windows-dockershim/1417250279195152384 The job above has two failed test cases...
Unable to parse the following SPDX file with `tvloader` package: ``` ... SPDXID: SPDXRef-File-34182904f819889b086a855ee5878f2a2e0b9037 FileChecksum: SHA1: 335029255dbadc3dfeb15c8e432078b1535b90de FileChecksum: SHA256: 0852707ebbd7e78d71c1eea3fb7ac0348aa22124a8975f787c07217058e0fe20 FileChecksum: SHA512: 2bca030aeb4aff21505267c02230bbc91bea728070fe6b46089eb7c168deeb6e0d40195a307d8e39073f322cba7abaf81a1b92011ca249eba2b8d92aedc10e38 ... ``` Got the following error: ```log...
**Reason for Change**: This PR introduces significant changes to the model access system, focusing on enabling downloads of model weights at runtime instead of packaging them in a container image....
**Is your feature request related to a problem? Please describe.** vLLM deployment crashed with the following error message:  Found this from vLLM repository: https://github.com/vllm-project/vllm/issues/9046. It works fine for tensor...
**Reason for Change**: Fully integrates supported_models.yaml as the source of truth for model metadata, replacing hardcoded ModelFamilyName and tag maps in model presets. **Changes:** - Updated `PresetParam` in `pkg/model/interface.go` to...
**Describe the bug** With the introduction of model weight download at runtime (#982), accessMode has become more confusing. There could be scenarios where a preset wants to download a "gated"...
**Describe the bug** Some models were added more than two years ago. We should deprecate and remove them in future releases. **Steps To Reproduce** **Expected behavior** **Logs** **Environment** - Kubernetes...
**Is your feature request related to a problem? Please describe.** > [!IMPORTANT] > Design Proposal Required Introduce a local caching mechanism to optimize the model weight download process in the...