kaito
kaito copied to clipboard
Kubernetes AI Toolchain Operator
It would be amazing to combine this with KEDA and the http scaler so the instances would scale to 0 when not in use.
Hi, Is there any roadmap to support other open source LLM's? If there is any documentation already in place, please share.
**Reason for Change**: Add adapter names to the logs in inference API Add log checks in e2e test to check if adapter is loaded successfully **Requirements** - [ ] added...
**Reason for Change**: Keep the docker sidecar container alive so incase ACR push fails we can still exec into the container to retrieve completed tuning job files in the /mnt/results...
Bumps [step-security/harden-runner](https://github.com/step-security/harden-runner) from 2.8.1 to 2.9.0. Release notes Sourced from step-security/harden-runner's releases. v2.9.0 What's Changed Release v2.9.0 by @h0x0er and @varunsh-coder in step-security/harden-runner#435 This release includes: Enterprise Tier - Telemetry...
Bumps [docker/login-action](https://github.com/docker/login-action) from 3.2.0 to 3.3.0. Release notes Sourced from docker/login-action's releases. v3.3.0 Bump @docker/actions-toolkit from 0.24.0 to 0.35.0 in docker/login-action#754 Bump https-proxy-agent from 7.0.4 to 7.0.5 in docker/login-action#741 Bump...
**Describe the bug** I'm trying to deploy a Phi-3 model in AKS, but every time I try to deploy the workspace, I get the following error: ``` kaito-rag/workspace-phi-3-medium-4k-instruct failed to...
**Reason for Change**: This PR adds OOM GPU Troubleshooting Section for tuning and inference
```[tasklist] ### Tasks - [ ] https://github.com/Azure/kaito/pull/357 - [ ] https://github.com/Azure/kaito/pull/360 - [ ] https://github.com/Azure/kaito/pull/364 - [ ] https://github.com/Azure/kaito/pull/518 - [ ] https://github.com/Azure/kaito/pull/602 - [x] Test: verify Kaito works on...