-
docker info: Server Version: 18.03.1-ce
the default method is: rr/round robin
FWM 278 rr
-
- #536 implemented a loadbalancer feature with only roundrobin algorithm.
- After #556 we should have a solid code base to easily implement different algorithms per route.
We want to have some o…
-
**Issue:**
When using ChangeFeedProcessor with Dedicated gateway, LeaseLostException is being constantly observed.
**Reason:**
For Dedicated gateway, the default MaxIntegratedCacheStaleness is 5…
-
/kind documentation
**Describe the solution you'd like**
Currently our project requires a lot of addition to the docs. I have made a list of few topics that we could add for better understanding o…
-
### 🎮 feature Request
As the app is dockerize then i think it is also good to apply kubernetes on that container because kubernetes helps as a load balancer when more user base use the app and also h…
-
Hi,
we would like to use coraza-spoa in production but unfortunately as soon as we put production traffic on it, after a few hours the coraza-spoa daemon "goes nuts", starts using up all available …
-
**Description:**
Currently, Valkey provides a dataset size calculation that estimates the total used memory minus the internal server struct sizes. However, this calculation does not account for inte…
-
### Library name
Azure.AI.OpenAI
### Please describe the feature.
**Summary**
This is to request a workaround or a support to be added into the OpenAIClient constructor that will allow to use cust…
dawwa updated
5 months ago
-
### Motivation.
The Fastchat-vLLM operational model offers significant advantages in deploying large language models (LLMs) for product services. [1](https://blog.vllm.ai/2023/06/20/vllm.html)
T…
-
This RFC proposes improvements to the management of Low-Rank Adaptation (LoRA) in vLLM to make it more suitable for production environments. This proposal aims to address several pain points observed …