Comments (3)
https://github.com/pytorch/pytorch/blob/main/c10/core/ScalarType.h#L55
from torch-mlir.
https://github.com/shouxieai/tensorRT_Pro/blob/main/onnx/onnx-ml.proto#L487
from torch-mlir.
checkpoint
https://github.com/jinchen62/torch-mlir/tree/dtype_support
https://github.com/jinchen62/llvm-project/tree/dtype_support
added float8 types to the op def, it could generates %78 = "llvm.fptrunc"(%76) : (vector<4xf32>) -> vector<4xf8E5M2>
, but it fails on https://github.com/llvm/llvm-project/blob/main/mlir/lib/Target/LLVMIR/TypeToLLVM.cpp#L79, and seems there is no support for float8 here https://github.com/llvm/llvm-project/blob/main/llvm/lib/IR/Type.cpp#L234
from torch-mlir.
Related Issues (20)
- Failed to lower torch.aten.slice.Tensor to linalg HOT 3
- Re-enable the disabled sparse tests due to roll PyTorch HOT 1
- [ONNX] Add support for onnx.Resize with nearest_mode "round_prefer_floor" and "round_prefer_ceil" HOT 6
- Failed to lower 'torch.operator "onnx.MaxPool"' to torch
- Failed to lower "torch.aten.sum.dim_IntList" to linalg HOT 6
- Failed to lower 'torch.operator "onnx.MaxPool"' to torch HOT 3
- Failed to lower 'torch.operator "onnx.AveragePool"' to torch (dilation) HOT 7
- Failed to lower "torch.aten.convolution" to linalg HOT 3
- Error lowering `index_put_`: 'tm_tensor.scatter' op mismatch in shape of indices and update value at dim#0 HOT 2
- Failed to lower batch normalization (in training mode)
- There is an incorrect hyperlink in docs/ltc_examples.md
- Failed to convert "onnx.Pad" into torch HOT 2
- convert-torch-onnx-to-torch generates invalid IR for onnx.Resize where scaling is in the first two dimensions
- aten.pad with mode = reflect is lowered wrong (numeric mismatch)
- [ONNX] Expand more ONNX operators as functions when importing HOT 1
- tm_tensor.scatter op mismatch in shape of indices and update value HOT 3
- Failed to lower "torch.operator "onnx.Pad"" with axes parameter
- Compile torch.nn.functional.scaled_dot_product_attention failed HOT 3
- [TorchONNXToTorch] Bug in PadOp pad tensor rearrangement HOT 2
- Remove optional tensor logic from linalg lowering for `IndexPutHackedTwinOp`
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 torch-mlir.