News for hackers. Stuff that matters.

mcharytoniuk

Ask HN: Async Python Adoption?

Are there any studies, large-scale polls, or anything about async coding adoption in Python?I wonder how widely the community accepts it, how widespread its usage is, and what the general sentiment is towards it.

( Read More... | no comments | on HN )
Re:Show HN: Open-Source Load Balancer for Llama.cpp on Monday June 03, 2024 @07:06AM (#40561453)
Yes, exactly. You can split the available context into "slots" (chunks) so it can handle multipe requests concurrently. The number of them is configurable.
Re:Show HN: Open-Source Load Balancer for Llama.cpp on Sunday June 02, 2024 @05:54AM (#40552836)
It divides the context into smaller "slots", so it can process requests concurrently with continuous batching. See also: https://github.com/ggerganov/llama.cpp/tree/master/examples/...
Re:Show HN: Open-Source Load Balancer for Llama.cpp on Sunday June 02, 2024 @05:53AM (#40552833)
Just open an issue if you need anything. I want to make it as good and helpful as possible. Every kind of feedback is appreciated.
Re:Show HN: Open-Source Load Balancer for Llama.cpp on Sunday June 02, 2024 @05:52AM (#40552830)
Currently, it is a single instance in memory, so it doesn't transfer state. HA is on the roadmap; only then will it need some kind of distributed state store.

Local states are reported by the agents installed alongside llama.cpp to the load balancer. That means they can be dynamically added and removed; it doesn't need a central configuration.

Re:Show HN: Open-Source Load Balancer for Llama.cpp on Sunday June 02, 2024 @05:50AM (#40552820)
In progress. I added that to the readme; I need the feature myself. :)

Show HN: Resonance – PHP Framework That Solves Real-Life Issues

https://github.com/distantmagic/resonance

Hello HN!I made a PHP framework with AI capabilities.The most important features: - Built on top of Swoole extension to support asynchronous features. - Opinionated, all-in-one solution for building web applications, particularly SaaS (it is not a boilerplate, though). - Integrates with llama.cpp to serve responses from open-source LLMs. - Uses minimal configuration and extensively relies on...

( Read More... | no comments | 2 points | on HN )