llvm
/
torch-mlir
mirror of https://github.com/llvm/torch-mlir
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
2,456 Commits
47 Branches
1195 Tags
77 MiB
Commit Graph

5 Commits (e581b33f9694204e12213f26b5de7b4b5126d6ea)

Author SHA1 Message Date
Rob Suderman f6f890520b
[torch][quant] Quantized `torch.mm` for linalg with end-to-end test (#2750) 
This includes custom op matching for decomposed operations and fusing
dequantization into dense operations. As a validation we compare
to the dequant+mm torch implementation.
 2024-01-24 14:02:50 -08:00
Rob Suderman dc37616d67
[torch][quant] Support quantize and dequantize for torch (#2731) 
Handle both `torch.dequantize` and `torch.quantize_per_tensor` including
the op based quantization parameter tracking. This includes adding
`qint32` to torch types as it was missing during the initial type
inclusion.

For testing we only have `torch.int8` and `torch.float` types on
function boundaries as the `qint8` types require passing the scale
and zero point quantization information which is not supported yet.
 2024-01-12 19:11:14 -08:00
Frederik Harwath 0860c41ee2 Implement aten.reflection_pad2d lowering to linalg 2024-01-10 21:32:22 -10:00
Xida Ren (Cedar) 6660a26594
lower torch.aten.isinf to linalg (#2638) 
Co-authored-by: Rob Suderman <rob.suderman@gmail.com>
 2023-12-28 17:20:32 -08:00
Stella Laurenzo 5eae0adff1
Breakup python pytorch deps (#2582) 
This lifts the core of the jit_ir_importer and ltc out of the pt1
project, making them peers to it. As a side-effect of this layering, now
the "MLIR bits" (dialects, etc) are not commingled with the various
parts of the pt1 project, allowing pt1 and ltc to overlay cleanly onto a
more fundamental "just MLIR" Python core. Prior to this, the Python
namespace was polluted to the point that this could not happen.

That "just MLIR" Python core will be introduced in a followup, which
will create the space to upstream the FX and ONNX pure Python importers.

This primary non-NFC change to the API is:

* `torch_mlir.dialects.torch.importer.jit_ir` ->
`torch_mlir.jit_ir_importer`.

The rest is source code layering so that we can make the pt1 project
optional without losing the other features.

Progress on #2546.
 2023-11-19 12:10:19 -08:00