My main question is whether when put into practical use, this can be measured in tokens/second, or more like 1 token per minute... I have seen locally hosted LLM that are as slow as 1 tok/second still be very useful if you give it a project to do something overnight and metaphorically walk away from it, check back with what it has done in 6 or 8 hours.
0.05 to 0.1 tok/s on the other hand, as reported in the URL for the lowest class of hardware, isn't really usable for much.
edit: I think this is a fantastic project in general concept, and look forward to seeing more efforts towards the general idea of being able to run a 350B to 900B size model locally, even if as slow as 1 tok/s, on hardware that ordinary people can afford. Anything along the general concept of "we have fast read NVME SSD storage, we have a big ass model on local disk, we'll read it at 11GB/tok as we need it, not try to load the whole thing".
In the readme you can see benchmark which everyone with different hardware is running Colibrì, and I have to say I've seen great times! I'm always doing more to improve!
I have a 16-core system with 256GB RAM here I could try it with but regretfully it's so old the CPUs aren't AVX2 capable. Otherwise it makes a fairly good llama-server test system for CPU only stuff. Oh well. Time to upgrade (painful to the wallet these days).
I was actually just working on the same thing as this, but I went down the route of mmapping the entire model into memory to avoid the extra ram usage. I also had Claude implement Medusa[1] on the model to try and avoid loading an additional model into memory but still get the benefits of MTP. Currently at a stop light so I can't list everything and I didn't get to read your full post either yet.
To expand since I just got home, I'm making all of my modifications to llama.cpp, the goal was to eventually put this on a SBC of some kind with an nvme to handle the mmapped files. I think the theoretical limit of my current setup is about 1.8 tok/s based on prior testing but that is also with the additional medusa heads not fully trained (I honestly don't know if the counting it's generated tokens or not.)
In the end it seems like the idea we had is similar, I just don't know how to write an llm parser/runner from scratch yet and instead of specifying what needed to stay in memory I just let the linux kernel handle it.
Oh last note, I also capped llama.cpp usage to 16GB of my 32GB, so it might be possible to get it down even lower.
Basically I kept needing an inference engine that could stream weights in and out as needed in an LRU manner. So I ended up vibe coding this thing that accepts a `--vram-budget` and stays under it (mostly). It turns out moving mmap'd bytes in and out of VRAM is way cheap compared to compute. Coupled with some pipelining/double-buffering, I almost always end up compute bound not memory bound. Granted I use way smaller models heh.
Pretty cool! I've also been playing around with GLM 5.2 this week and was equally impressed. At work we're running it locally on some crazy expensive hardware as a test before starting another project so it's great to see people taking this massive FOSS model release and running it on an average machine, even if it's not terribly practical at this point.
I'm not fully understanding this business of MoE so please forgive me if this is a dumb question, but would it be possible to use MPI with a small cluster to distribute the load?
I think if you had something like a theoretical used/refurb 2U rackmount server with two older multi core CPUs, 768GB of RAM, you would see faster performance loading a Q6 or Q8 GGUF of GLM5.2 into a freshly-compiled latest copy of llama-server, with the "no-mmap" option turned on to intentionally load the whole thing into RAM at the time the llama-server daemon launches.
If you want a CPU-only machine with 512GB to 1024GB of RAM, despite extreme cost rises, there are still some great options out there from companies selling ex-lease stuff that's 3, 4, 5 years old. It'll be loud as hell under full CPU load when running inference, so if you plan to use it at home, put it in your garage or basement or laundry room or somewhere similar on the far end of a network cable.
The software that OP has published appears to be specifically designed to hold only the active parameters in RAM (<100GB) and read content off local NVME SSD as needed on the fly. All that NVME SSD read wouldn't be necessary if you can hold the model in RAM, even in the absence of any GPUs.
What causes problems is the rewriting in this case are only read while writing is the cache! However, I'm working to improve more and more and make some parts lighter!
0.05 to 0.1 tok/s on the other hand, as reported in the URL for the lowest class of hardware, isn't really usable for much.
edit: I think this is a fantastic project in general concept, and look forward to seeing more efforts towards the general idea of being able to run a 350B to 900B size model locally, even if as slow as 1 tok/s, on hardware that ordinary people can afford. Anything along the general concept of "we have fast read NVME SSD storage, we have a big ass model on local disk, we'll read it at 11GB/tok as we need it, not try to load the whole thing".
To expand since I just got home, I'm making all of my modifications to llama.cpp, the goal was to eventually put this on a SBC of some kind with an nvme to handle the mmapped files. I think the theoretical limit of my current setup is about 1.8 tok/s based on prior testing but that is also with the additional medusa heads not fully trained (I honestly don't know if the counting it's generated tokens or not.)
In the end it seems like the idea we had is similar, I just don't know how to write an llm parser/runner from scratch yet and instead of specifying what needed to stay in memory I just let the linux kernel handle it.
Oh last note, I also capped llama.cpp usage to 16GB of my 32GB, so it might be possible to get it down even lower.
[1] https://arxiv.org/abs/2401.10774
Basically I kept needing an inference engine that could stream weights in and out as needed in an LRU manner. So I ended up vibe coding this thing that accepts a `--vram-budget` and stays under it (mostly). It turns out moving mmap'd bytes in and out of VRAM is way cheap compared to compute. Coupled with some pipelining/double-buffering, I almost always end up compute bound not memory bound. Granted I use way smaller models heh.
Nice work!
In theory MPI could distribute experts across nodes. In practice, for small clusters the added network latency usually hurts more than it helps.
Better suited for big clusters with fast interconnects. For now we're focusing on single-machine speed (caching, GPU hybrid, etc.).
If you want a CPU-only machine with 512GB to 1024GB of RAM, despite extreme cost rises, there are still some great options out there from companies selling ex-lease stuff that's 3, 4, 5 years old. It'll be loud as hell under full CPU load when running inference, so if you plan to use it at home, put it in your garage or basement or laundry room or somewhere similar on the far end of a network cable.
The software that OP has published appears to be specifically designed to hold only the active parameters in RAM (<100GB) and read content off local NVME SSD as needed on the fly. All that NVME SSD read wouldn't be necessary if you can hold the model in RAM, even in the absence of any GPUs.
https://github.com/JustVugg/colibri#ssd-wear-warning
Amazing job!