Comments (3)
justinchuby
commented on July 27, 2024
Collective ops are being discussed in ONNX IIRC. Could you explain how you plan to use them or how they should appear in the graph? Thanks!
from onnxscript.
vincent-mayer
commented on July 27, 2024
Thanks for the response @justinchuby! I saw this onnx issue microsoft/onnxruntime#8244 and this talk from an Nvidia engineer, but not that much seems to have happened addressing the issues mentioned in the talk.
StableHLO another portability layer similar to onnx has added those operations, see here. Essentially we would like to be able to express model sharding and where collective operations have to be inserted into the graph on the python-level and export those annotations/ops via the onnx IR to later consume them in the compiler. For an example usage in python see tensorrt-llm here.
from onnxscript.
justinchuby
commented on July 27, 2024
cc @gramalingam if you can share more info
from onnxscript.
Related Issues (20)
- Transformations that impact graph outputs
- Add onnx.checker.check_model into optimizer/rewriter HOT 2
- Dynamo models from torchbench has duplicated opset imports
- [IR] `copy_from` method for transferring metadata
- Pass to convert a model with bfloat16 inputs to float16 HOT 4
- Optimizer produces a wrong model if run after it is optimized and inlined HOT 1
- [torchlib] native_layer_norm_float32 is failing on MacOS CI with significant absolute difference HOT 5
- ConstantFolder fails shape inference on second iteration HOT 3
- [IR] Common passes
- [IR] Dead code elimination pass
- Atomicity in optimization/rewrite passes HOT 1
- [rewriter/optimizer] Port ORT-model-conversion tools and integrate Optimizer and Rewriter Tools
- [tracking] Enable dynamo_export tests for python=3.12
- [Rewriter] Why doesn't it match?
- Use SVG from netron in documentations
- [IR] Tensor todos
- [IR] Values that are initialized but not graph inputs do not have their ValueInfo preserved HOT 2
- [IR] Allow values as outputs to ir.Node initializer HOT 3
- Issue in gemm_to_matmul_add
- Optimizer failure on the phi-3 model
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 onnxscript.