llama.cpp: don't sleep on --split-mode tensor

github.com

llama.cpp: don't sleep on --split-mode tensor

github.com

robber@lemmy.ml to

LocalLLaMA@sh.itjust.worksEnglish · 4 days ago

ggml: backend-agnostic tensor parallelism (experimental) by JohannesGaessler · Pull Request #19378 · ggml-org/llama.cpp

github.com

This PR adds initial support for tensor parallelism, enabled via specifying --split-mode tensor. This should be considered as an experimental feature that is not yet production ready. In principle ...

In case you missed it, 2-3 weeks ago, experimental tensor-parallelism support was merged into llama.cpp.

In a nutshell, this allows in multi-GPU setups to not only combine the VRAM of the cards but also their computing power. The results depend a lot on the specific setup and model, but on my 3x RTX 2000e Ada rig running Qwen3.6-35b it almost doubled generation throughput (these are low-powered cards which are not very powerful on their own).

The option to turn it on is --split-mode tensor.

It’s not yet officially documented, I assume because it’s still experimental. But since #22362 was merged yesterday, in my case it now also work for the latest Qwen3.6 models.

You must log in or # to comment.

Chat

LocalLLaMA@sh.itjust.works

localllama@sh.itjust.works

Create a post

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: [email protected]

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they’re still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

6 users / day
35 users / week
56 users / month
62 users / 6 months
1 local subscriber
4.69K subscribers
50 Posts
100 Comments
Modlog