Flyte enables production-grade orchestration for machine learning workflows and data processing created to accelerate local workflows to production.

Flyte

<https://github.com/flyteorg/flyte-sdk/pull/387|#387 Implement VLLMAppEnvironment and SafeTensorStreaming>
Pull request opened by <https://github.com/cosmicBboy|cosmicBboy>
This PR introduces a VLLMAppEnvironment app environment to support serving vllm apps, and a SafeTensorStreaming class to load weights directly from remote storage into memory.
<https://github.com/flyteorg/flyte-sdk|flyteorg/flyte-sdk>

<https://github.com/flyteorg/flyte-sdk/pull/387|#387 Implement VLLMAppEnvironment and SafeTensorStreaming>
Pull request merged by <https://github.com/kumare3|kumare3>
<https://github.com/flyteorg/flyte-sdk|flyteorg/flyte-sdk>