Felix Schneider 0314188dbe [torch] Basic support for per-channel quantized graphs (#3623) ... This patch adds basic support for lowering graphs with per-channel quantization. Per-channel quantized ops have to be excluded from `FuseQuantizedOps` for now but can be used in QDQ quantized form. Using this patch, we're able to import and execute (on the linalg backend) graphs with per-channel quantization applied using the "new" PyTorch 2.0 Export Quantization.		2024-08-10 15:51:09 +02:00
..
GlobalizeObjectGraph	[torch-mlir][test] cleanup trailing whitespace in mlir files (#2806)	2024-01-25 14:24:13 -08:00
adjust-calling-conventions.mlir	[torch-mlir] bump stablehlo/llvm version (#3471)	2024-06-18 16:59:53 -07:00
canonicalize.mlir	[torch] Unpacking sometimes misses shape inference (#3609)	2024-08-08 16:17:31 -07:00
decompose-complex-ops-legal.mlir	handles 2,3,4 from https://github.com/llvm/torch-mlir/issues/1963 (#1964)	2023-03-24 21:50:01 -05:00
decompose-complex-ops.mlir	[Torch] Add support for static uneven divisible AdaptiveAvgPool2d (#3566)	2024-08-01 11:37:53 +08:00
drop-abstract-interp-calculations.mlir	[custom op] Generalize shape library logic to work with dtypes (#1594)	2022-12-13 08:25:41 -08:00
erase-module-initializer.mlir	Iteratively run the main simplification pipeline.	2022-08-17 14:54:33 -07:00
fuse-quantized-ops.mlir	Adds misc fixes for some padding related issues (#3528)	2024-07-11 20:01:45 -05:00
inline-global-slots-analysis.mlir	Rework how global slot initializers work.	2022-08-08 18:12:06 -07:00
inline-global-slots-transform.mlir	Rework how global slot initializers work.	2022-08-08 18:12:06 -07:00
invalid.mlir	Representing Symbolic Shape Expressions in Torch Dialect (#3372)	2024-06-07 04:04:03 -07:00
lower-to-backend-contract-error.mlir	Allow running DecomposeComplexOps more than once (#1671)	2022-12-08 09:26:38 -08:00
match-quantized-customs-ops.mlir	[torch] Basic support for per-channel quantized graphs (#3623)	2024-08-10 15:51:09 +02:00
maximize-value-semantics.mlir	Add alias analysis for cast-like ops to maximize-value-semantics (#2160)	2023-05-25 17:05:41 +00:00
ops.mlir	Register fake_quantize related ops (#3522)	2024-07-05 11:02:03 -07:00
prepare-for-globalize-object-graph.mlir	mlir: bump llvm tag to 5380e3 (#856)	2022-05-16 12:54:35 -07:00
reduce-op-variants-error.mlir	mlir: bump llvm tag to 5380e3 (#856)	2022-05-16 12:54:35 -07:00
reduce-op-variants.mlir	[torch] Fix tm_tensor.attention for end-to-end (#2907)	2024-02-13 21:18:01 -08:00
refine-public-return.mlir	Support `DerefineOp` in `RefinePublicReturn`.	2023-07-20 20:08:46 +02:00
reify-dtype-calculations.mlir	Breakup python pytorch deps (#2582)	2023-11-19 12:10:19 -08:00
reify-shape-calculations.mlir	Cast `number` to `float` when shape function takes Scalar arg (#1978)	2023-03-28 09:30:31 -07:00
scalarize-shapes.mlir	[torch] Improve shape inference for `torch-to-linalg` path for reshapes (#3055)	2024-03-26 12:41:40 -07:00
simplify-dtype-calculations.mlir	[MLIR][TORCH] Add E2E support for view_as_real op (#2419)	2023-09-01 21:12:01 -07:00
simplify-shape-calculations.mlir	[torch-mlir][test] cleanup trailing whitespace in mlir files (#2806)	2024-01-25 14:24:13 -08:00
torch-function-to-torch-backend-pipeline.mlir	[Torch Dialect] fix torch.uint8's dtype infer (#2227)	2023-06-13 10:38:20 +08:00
torch-nary-canonicalize.mlir	[torch] Folders for `torch.aten.*.tensor` operators [add, sub, mul] (#2878)	2024-02-19 10:28:23 -08:00
verify-backend-contract-error.mlir	Clean up verification of calling conventions.	2023-07-20 20:08:46 +02:00
verify-backend-contract-unimplemented-op.mlir	LowerToBackendContract: Explicitly error out on unimplemented operator (#1947)	2023-03-20 16:27:08 +01:00