Comments (2)
It's bandwidth. The model is bottlenecked by how quickly the processor can fetch weights from RAM. FP16 consumes 4x as many bits as Int4, and thus is 4x slower.
from llama_mps.
Hi, I wish I could give you a definitive answer, but unfortunately I am not familiar enough with PyTorch' MPS implementation to be able to confirm or deny your theory...
from llama_mps.
Related Issues (15)
- RuntimeError: probability tensor contains either `inf`, `nan` or element < 0 HOT 2
- Trial runs at Llama 7B (success) and 65B (fail) HOT 2
- Huggingface weights repo doesn't have params.json HOT 1
- Support Apple Neural Engine (ANE) Transformers HOT 1
- Corrupted output due to PyTorch MPS issue affecting torch.argmax() and torch.multinomial() HOT 3
- RuntimeError: Cannot set version_counter for inference tensor
- powermetrics
- What changes were made for MPS support?
- op Height/Width dimensions must be less than 16384
- AssertionError: ./models/tokenizer.model HOT 1
- Garbage output on 30B model? HOT 10
- MPS device support HOT 1
- Fine tuning LLaMA on Apple Silicon GPUs HOT 2
- The magnet link of the model resource seem to be unusable HOT 2
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 llama_mps.