llama.cpp VS llama

well https://github.com/ggerganov/llama.cpp/issues/6849

Have just done this recently for local chat with pdf feature in https://recurse.chat. (It's a macOS app that has built-in llama.cpp server and local vector database)

Running an embedding server locally is pretty straightforward:

- Get llama.cpp release binary: https://github.com/ggerganov/llama.cpp/releases

Ah, thanks for this! I can't edit my parent comment that you replied to any longer unfortunately.

As I said, I only compared the contributors graphs [0] and checked for overlaps. But those apparently only go back about year and only list at most 100 contributors ranked by number of commits.

[0]: https://github.com/ollama/ollama/graphs/contributors and https://github.com/ggerganov/llama.cpp/graphs/contributors

KodiBot is a desktop app that enables users to run their own AI chat assistants locally and offline on Windows, Mac, and Linux operating systems. KodiBot is a standalone app and does not require an internet connection or additional dependencies to run local chat assistants. It supports both Llama.cpp compatible models and OpenAI API.

There are already some implementations out there which attempt to accomplish this!

Here's an example: https://github.com/silphendio/sliced_llama

A gist pertaining to said example: https://gist.github.com/silphendio/535cd9c1821aa1290aa10d587...

Here's a discussion about integrating this capability with ExLlama: https://github.com/turboderp/exllamav2/pull/275

And same as above but for llama.cpp: https://github.com/ggerganov/llama.cpp/issues/4718#issuecomm...

For those who might not be aware of this, there is also an open source project on GitHub called "Twinny" which is an offline Visual Studio Code plugin equivalent to Copilot: https://github.com/rjmacarthy/twinny

It can be used with a number of local model services. Currently for my setup on a NVIDIA 4090, I'm running both the base and instruct model for deepseek-coder 6.7b using 5_K_M Quantization GGUF files (for performance) through llama.cpp "server" where the base model is for completions and the instruct model for chat interactions.

llama.cpp: https://github.com/ggerganov/llama.cpp/

deepseek-coder 6.7b base GGUF files: https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-GGU...

deepseek-coder 6.7b instruct GGUF files: https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct...

> All the magic of "7B LLaMA running on a potato" seems to involve lowering precision down to f16 and then further quantizing to int4.

LLaMa weights are f16s to start out with, no lowering necessary to get to there.

You can stream weights from RAM to the GPU pretty efficiently. If you have >= 32GB ram and >=2GB vram my code here should work for you: https://github.com/gmorenz/llama/tree/gpu_offload

There's probably a cleaner version of it somewhere else. Really you should only need >= 16 GB ram, but the (meta provided) code to load the initial weights is completely unnecessarily making two copies of the weights in RAM simultaneously.

My code for this is very much not high quality, but I have a CPU + GPU + SSD combination: https://github.com/gmorenz/llama/tree/ssd

Usage instructions in the commit message: https://github.com/facebookresearch/llama/commit/5be06e56056...

At least with my hardware this runs at "[size of model]/[speed of SSD reads]" tokens per second, which (up to some possible further memory reduction so you can run larger batches at once on the same GPU) is a good as it gets when you need to read the whole model from disk each token.

At a 125GB and a 2MB/s read (largest model, what I get from my ssd) that's 60 seconds per token (1 day per 1440 words), which isn't exactly practical. Which is really the issue here, if you need to stream the model from an SSD because you don't have enough RAM, it is just a fundamentally slow process.

You could probably optimize quite a bit for batch throughput if you're ok with the latency though.

I don't know about this fork specifically, but in general yes absolutely.

Even without enough ram, you can stream model weights from disk and run at [size of model/disk read speed] seconds per token.

I'm doing that on a small GPU with this code, but it should be easy to get this working with the CPU as compute instead (and at least with my disk/CPU, I'm not even sure that it would run even slower, I think disk read would probably still be the bottleneck)

https://github.com/gmorenz/llama/tree/ssd