Comments (1)
You just separate them with spaces like so:
./dllama inference ... --workers 10.0.0.2:9998 10.0.0.3:9998 10.0.0.4:9998
You can also run several from the same IP, like so:
./dllama inference ... --workers 10.0.0.1:9996 10.0.0.1:9997 10.0.0.1:9998
As for 1. performance on workers that have unified memory would be faster due to their increased memory bandwidth.
The root node consumes a bit more memory than the workers so I'd use the 36gb macbook as the root node, though typically it divides the memory required to load the model by the amount of workers though the number of workers need to be a power of 2 so 2, 4, 8 workers etc.
Also it's worth experimenting with the number of threads you specify, in my case I have 6 cores and 12 threads, but I get the best performance by using 8 threads.
Larger models require more data transferred during each inference pass, something like Q80 Llama 70B might already hit the limits of gigabit ethernet, switching capacity of your ethernet switch also becomes a factor then.
from distributed-llama.
Related Issues (20)
- terminate called after throwing an instance of 'ReadSocketException' HOT 35
- Vulkan Acceleration HOT 35
- How To Add Suppoerted Model HOT 2
- network utilization HOT 3
- (Crashing on Low Memory SBC) main invoked oom-killer: gfp_mask=0x1100dca(GFP_HIGHUSER_MOVABLE|__GFP_ZERO), order=0, oom_score_adj=0 HOT 51
- Support for another models (ollama models) HOT 3
- [Feature Suggest] From All-Reduce to Ring-All-Reduce HOT 1
- Support nSlices > nKvHeads
- [Feature Suggest] Config File alternative to Command Line Arguments HOT 2
- Request: Community Discord? HOT 1
- convert into .bin HOT 2
- support multi nvidia jetson agx orin? HOT 3
- master and worker started but with problems HOT 5
- float-type f32 will not start HOT 2
- dllama-api hosted on 127.0.0.1 HOT 2
- dllama-api invokes "what(): Invalid tokenizer file " HOT 2
- what(): Cannot create socket HOT 1
- What about mobile phones? HOT 4
- Exception: max_seq_len is required, please update params.json with convert-llama.py on Meta-Llama-3-8B-Instruct
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from distributed-llama.