Comments (9)
Ok, I got F1 = 0.601 when I changed the max_new_tokens
from 10 to 100, which is understandable considering how this is calculated.
The best performance I got is 5.03.
from ampere_model_library.
Oh, and accuracy values I've provided were gathered with --num_runs=5.
from ampere_model_library.
Which transformers branch are we using for this? Here:
https://github.com/AmpereComputingAI/transformers/commits/karol/llama-compile-v2
the only change from original repo is to remove some validation checks which fail with Pytorch 2.1.
from ampere_model_library.
that's what we use - somehow it's very slow vs latest upstream - maybe they've introduced some significant improvements since our branching out? @dkupnicki please check when possible
from ampere_model_library.
Ok, you are comparing vs latest upstream. I think we may just rebase my branch on it. I see there was some work going over there, but didn't expect such difference. If AIO is generating same graph we can safely switch to newer implementation. Also numbers you are much lower than what I observed. Which version of pytorch-AIO and native pytorch have you used for this benchmarks? How long sequences are you generating.
I was having around ~9 tps in FP16 mode and around 5 tps in FP32 mode with AIO.
from ampere_model_library.
I can’t reproduce this issue. I tried with different versions of transformers, with and without AIO, with and without torch.compile() and I’m always getting the same 0.313 result.
from ampere_model_library.
Ok, I will check. What about performance? Can you get to 9 tps?
from ampere_model_library.
It was fp32 BTW, checking fp16 now
from ampere_model_library.
I guess we've solved that one. Closing. Thanks to you Daniel and Karol for your input.
from ampere_model_library.
Related Issues (20)
- Add Int8 BERT from MLPerf (PyTorch)
- Add support for torch.jit.trace() models to Pytorch. HOT 1
- Some models fail without AIO with with uncorrect batch sizes
- Pytorch models needs two warmup runs HOT 1
- Cache pytorch models after tracing/scripting HOT 1
- VGG16 fails in Pytorch HOT 3
- AML should support AIO_NUM_THREADS="all" HOT 2
- Missing TBTracer HOT 1
- Add fp16 PyTorch models HOT 3
- --disable_jit_freeze flag is not working in many Pytorch models HOT 2
- Add NHWC Pytorch torchvision models HOT 3
- Pytorch Roberta Base Squad fails accuracy tests HOT 2
- 2x performance drop using pytorch depending on how input data is fed into model HOT 10
- Nano GPT model
- Issues running AML on amperecomputingai/onnxruntime:1.8.0 image HOT 2
- Add read-mes HOT 1
- CI test for model_zoo HOT 1
- Help users lay hands on datasets / models easily
- Move models / other stuff to S3 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 ampere_model_library.