LocalLLaMA

3 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago

MODERATORS

communick@poweruser.forum

Any way to decrease inference time during long chats?(+decrease repetition without breaking things) (alien.top)

submitted 11 months ago by The_One_Who_Slays@alien.top to c/localllama@poweruser.forum

5 comments fedilink hide all child comments

Using Oobabooga's Webui on cloud.

I haven't noticed that immediately, but apparently once I breach the context limit, or some short time after the fact, the inference time increases significantly. For example, in the beginning of the conversation a single message goes about 13-16 tps. After reaching the threshold, the speed starts decreasing until it becomes around 0.1 tps.

Not only that, but the text also starts repeating. For example, character's certain features or their actions start coming up in almost every sunsequent message with almost identical wording, like some sort of a broken record. It's not impossible to stir the plot forward, but it gets tiring, especially considering a huge delay on top of that.

Is there any solution or a workaround to these problems?

you are viewing a single comment's thread
view the rest of the comments

[–] out_of_touch@alien.top 1 points 11 months ago (2 children)

Interesting timing, I don't know if this exists yet or not but I was just thinking about a feature that would use like a range for context size.

The idea would be that you specify a min and a max context, say 6k and 8k and the way it would work is when you breach the 8k max, instead of just cutting it off there, it would go further forward and cut it off at 6k and then it would build on that context until it once again reached 8k and keep repeating the process after that. This would make it so that instead of reprocessing the entire context every time, it would only need to do it when the max was exceeded. I'm a programmer by trade so I'm kind of tempted to look into building this but I haven't even looked into what that requires or if the feature already exists out there somewhere.

[–] The_One_Who_Slays@alien.top 1 points 11 months ago

That would be amazing. I think something like that could even be included into ooba's official extension repo.

[–] LocoLanguageModel@alien.top 1 points 11 months ago

I think koboldCPP already does this unless I'm misunderstanding, have a look at this:

Context Shifting is a better version of Smart Context that only works for GGUF models. This feature utilizes KV cache shifting to automatically remove old tokens from context and add new ones without requiring any reprocessing. So long as you use no memory/fixed memory and don't use world info, you should be able to avoid almost all reprocessing between consecutive generations even at max context. This does not consume any additional context space, making it superior to SmartContext. Context Shifting is enabled by default, and will override smartcontext if both are enabled. Your outputs may be different with shifting enabled, but both seem equally coherent. To disable Context Shifting, use the flag --noshift.