[i386]

This was done on my home lab simulating 5ms latency and jitter between machines. Splits work quite well if you your nodes are over WAN at metro latency’s but not super fast on global WAN.

The idea is that you could take several machines without dedicated RDMA or NVLINK fabric and use them to serve a large model on hardware you own then share it with others.

I’m currently working on GLM 5.2 on my lab environment with around 10 tok/s on the same split.

[zdw]

What hardware (CPU/GPU/memory) and network was used for this? What quantization for GLM 5.2? How much tuning of the split was needed?

[i386]

The lab features two Mac Studios: an Apple M3 Ultra (32 CPU cores, 80 GPU cores, 256 GB unified memory) and an Apple M1 Ultra (20 CPU cores, 48 GPU cores, 128 GB unified memory), both connected via 1Gbit Ethernet.

We use a customized Q2 quantization that preserves sensitive tensors at Q8.

To reduce compute time per layer, we are developing a custom GLM DSA Metal graph.

While we are not yet approaching MTP, we plan to port our existing MTP implementations from versions 4.7 and 5.1 to 5.2.

Since GLM's MTP acceptance rate is very high for a single predicted token, we are exploring token prediction techniques to widen the predicted tokens and utilize parallelism for verification.

[wlesieutre]

Equivalent M3 machines no longer for sale from Apple (only up to 96 GB) but can be had on eBay for around $14,000 each

[drawnwren]

It's notable that they're so valuable because they feature 800Gbps of memory bandwidth. About twice what's available on the top end of M5, and exactly what makes llm inference fast.

[embedding-shape]

> because they feature 800Gbps of memory bandwidth. About twice what's available on the top end of M5

Ouch, about half of the memory bandwidth of a dedicated GPU though :/ Running LLMs on Apple hardware still doesn't make any sense to me.

[khalic]

M5 max has 614GB/s, you mean the m4?

[drawnwren]

Oh, I was looking at every M5 except for the 40-core M5 Max. They have 460.

[SwellJoe]

That sounds cool, but it's still pretty meaningless without information about what your home lab looks like. A few DGX Sparks wired up with their fancy super fast network is much different than a few laptops on wifi.