[curious_cat_163]

> a stateful load balancer that is aware of each server's available slots

Interesting. Curious to understand what a 'slot' is, in this context.

Is that a llama.cpp specific application-layer state that llama.cpp makes available? Or is this an application-layer state that is being inferred? If later, how?

[kherud]

I think this comment explains it https://github.com/ggerganov/llama.cpp/discussions/4130#disc... As far as I understand (and mcharytoniuk should better confirm this), llama.cpp allows to chunk the context window of an LLM into independent blocks, such that multiple requests can be processed in a single inference. I think due to the auto-regressive nature of LLMs, you also don't have to wait for all sequences to finish to output them. As soon as one sequence finishes, you can use its "slot" in the context window for other requests.

[mcharytoniuk]

Yes, exactly. You can split the available context into "slots" (chunks) so it can handle multipe requests concurrently. The number of them is configurable.

[tjfontaine]

Looks like it’s to only have one completion running at a time currently, https://github.com/distantmagic/paddler/blob/main/loadbalanc... I was curious if there was any other cache tracking happening

[mcharytoniuk]

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.

[riedel]

What does stateful mean: I always wonder how loading states of users is done, it seems that one can call `llama_state_set_data` , does this load balancer create a central store for such states? What is the overhead of transfering state?

[mcharytoniuk]

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.

[asne11]

"slot" is a processing unit. Either GPU or CPU. I believe `llama.c` is only CPU so I'm guessing 1 slot = 1 core (or thread)?

[mcharytoniuk]

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/...

[kgeist]

Llama.cpp can run on CPU, on GPU, or in mixed mode (some layers run on CPU and some on GPU if you don't have enough VRAM).

[new299]

llama.cpp is not CPU only…

[BoredPositron]

Probably just free accelerators.