"test/vscode:/vscode.git/clone" did not exist on "f201285c8cd08a1140090be6bd3bffcb0746775f"
- 11 Oct, 2023 10 commits
-
-
charlie authored
-
charlie authored
-
Paul Fultz II authored
-
Ted Themistokleous authored
* Fix scatter operator for nonstandard shapes remove standard() shape check for scatter inputs. * Add nostandard input tests for scatter --------- Co-authored-by:Chris Austen <causten@users.noreply.github.com>
-
Artur Wojcik authored
-
Artur Wojcik authored
-
Artur Wojcik authored
-
Artur Wojcik authored
-
Artur Wojcik authored
-
Artur Wojcik authored
-
- 10 Oct, 2023 7 commits
-
-
Artur Wojcik authored
-
Michał Gallus authored
-
charlie authored
-
charlie authored
-
charlie authored
-
charlie authored
-
Ted Themistokleous authored
-
- 06 Oct, 2023 6 commits
-
-
Krzysztof Drewniak authored
-
Paul Fultz II authored
-
Lakhinder Walia authored
-
Artur Wojcik authored
-
Charlie Lin authored
-
Artur Wojcik authored
-
- 04 Oct, 2023 2 commits
-
-
Artur Wojcik authored
-
Zakor Gyula authored
-
- 03 Oct, 2023 3 commits
-
-
Umang Yadav authored
-
Charlie Lin authored
Makes ConstantOfShape work with a variable dimensions input
-
Umang Yadav authored
-
- 29 Sep, 2023 2 commits
-
-
Umang Yadav authored
add flags for ck, Enable CK with hipRTC. CK can be used with the MIGRAPHX_ENABLE_CK=1 and MIGRAPHX_TUNE_CK=1
-
Chris Austen authored
Enable MLIR performance enhancements with MIGRAPHX_ENABLE_MLIR=1
-
- 28 Sep, 2023 4 commits
-
-
Ted Themistokleous authored
-
Paul Fultz II authored
-
Charlie Lin authored
-
Umang Yadav authored
MIGraphX verification by default uses normalized RMS error as the basis for the verification. This change adds some logic to allow migraphx to do "np.allclose" type of elementwise verification using atol and rtol. Commit also includes changes to consistently pass "gold" or "expected" results as the second argument for "verify_range()" calls. Default RMS tolerance inside driver is set to 0.001 which IMO is high for FP32 compared to what we had earlier. Need better defaults
-
- 27 Sep, 2023 6 commits
-
-
Ted Themistokleous authored
Modify reshapes to use reshape_lazy for aliasing and then reshape for a reshape copy operation to eliminate contiguous
-
Krzysztof Drewniak authored
Currently, the is_mlir_conv predicate wasn't being used when offloading standalone convolutions to MLIR on Navi3x, which caused failures relating to being unable to construct the MLIR program when a 3D convlolution was passed in. This commit amends the standalone lowering to use said predicate, as well as to include quant_convolution and quant_dot into the set of operations that get a standalone lowering.
-
ravil-mobile authored
-
Krzysztof Drewniak authored
Add mlir_logger, which registers a MLIR diagnostic handler that captures any information generated by a MLIR compile and saves it to a string. This will be useful during tuning, where some such errors may be the result of an inapplicable tuning configuration and should be suppressed.
-
Paul Fultz II authored
-
Umang Yadav authored
-