amit

FEATURE REQUEST: cpu percentage should be calculated with respect to "cpu request/limit"

2

Currently the CPU percentage is calculated with respect to the system cpus. In the word on VMs and distributed system, the actual CPU of a specific node is not that...

how to use the access token for http api calls to lambdas with cognito authorisers?

3

Hi, Thanks for the library, while manage to obtain a user access token, i failed to understand how to user it with http requests to lambdas that use cognito authorisers....

feature request: release for linux arm64

2

It will be awesome to have more releases a) `linux ARM64` and b) `macOS-arm64`. I would like to use this CLI in linux docker running over Apple M1 computer.

Fine tuning training for a mix language tessdata

6

If understand correctly, traineddata files that starts with a capital letter are "mixed languages" traineddata (e.g Hebrew = heb+eng). Was is produced by combining "heb" and "eng" traineddata files or...

PVC get deleted on clean up (when bound by a Deployment)

15

I've used minio as part of a release in Skaffold (sub-chart). [link](https://github.com/helm/charts/tree/master/stable/minio) The helm value of the minio: persistence.enabled is set to true, and a PVC is created for its...

how to accept a binary file

1

I'm attempting to crate a lambda function in python that accepts an image file via a POST request. I've managed to config your plugin to my serverless service, and indeed...

[Core] feat: Implement Priority Scheduling in V1 Engine

1

This commit introduces priority scheduling capabilities to the V1 LLM engine. Key changes include: 1. **`EngineCoreRequest` and `Request` updates:** * Added a `priority` field to `EngineCoreRequest` and `Request` classes to...

[Core] feat: Implement Priority Scheduling in V1 Engine

6

This commit introduces priority scheduling capabilities to the V1 LLM engine. Key changes include: EngineCoreRequest and Request updates: Added a priority field to EngineCoreRequest and Request classes to carry priority...

# Add New LoadBalancingStrategy: RoutingKey This PR introduces a new load balancing strategy, **RoutingKey**, alongside the existing strategies LeastLoad and PrefixHash. ## 🚦 Behavior • **When RoutingKey is selected**, the...