| .. |
|
codegen
|
Revert "[inductor] Avoid bool being upcast to int (#109913)"
|
2023-12-20 12:33:50 +00:00 |
|
fx_passes
|
Support Predispatch functionalization (#113728)
|
2023-12-19 20:28:35 +00:00 |
|
kernel
|
[OAT] toggle for forcing matmul precision matching (#115326)
|
2023-12-07 20:22:12 +00:00 |
|
__init__.py
|
Make dynamo configs more amenable to static type checking (#112130)
|
2023-11-08 21:17:45 +00:00 |
|
autotune_process.py
|
Remove yet more type-ignores in dynamo/inductor (#114684)
|
2023-11-28 22:09:38 +00:00 |
|
bounds.py
|
[inductor] Parameterize ir.Scan on combine_fn (#109132)
|
2023-12-12 16:30:50 +00:00 |
|
codecache.py
|
Back out "[aotinductor] replace lld with the default ld linker (#115478)" (#115875)
|
2023-12-15 05:56:06 +00:00 |
|
comm_analysis.py
|
Delete a bunch of type-ignores (#113990)
|
2023-11-18 02:48:38 +00:00 |
|
comms.py
|
[AOTI][refactor][2/n] Rename kernel to python_kernel_name (#115766)
|
2023-12-15 03:08:13 +00:00 |
|
compile_fx.py
|
[Inductor][Observability] Change to log.debug to avoid excessive long of logs (#115474)
|
2023-12-17 00:25:54 +00:00 |
|
config.py
|
[PyTorch] AOTI: add minimal arrayref interface (#112800)
|
2023-12-13 12:06:35 +00:00 |
|
constant_folding.py
|
[Inductor] Fix constant folding and extern kernel mutation tracking bugs (#115908)
|
2023-12-19 02:06:50 +00:00 |
|
coordinate_descent_tuner.py
|
Fix typo under torch/_inductor directory (#110530)
|
2023-10-05 02:17:20 +00:00 |
|
cudagraph_trees.py
|
Revert "Serve multistream graph captures from correct pool (#114647)"
|
2023-12-20 17:11:42 +00:00 |
|
debug.py
|
[inductor] add a config to specify the shape attribute for the generated svg graphs (#114811)
|
2023-11-30 06:10:37 +00:00 |
|
decomposition.py
|
[inductor] Fix angle decomposition return type (#115700)
|
2023-12-13 14:16:31 +00:00 |
|
dependencies.py
|
A fix for reduction + pointwise + multi-level reduction optimization (#112935)
|
2023-11-21 20:34:07 +00:00 |
|
exc.py
|
[AOTInductor] Improve validation for C++ wrapper codegen (#111102)
|
2023-10-13 08:46:17 +00:00 |
|
freezing.py
|
FF inductor failure (#114980)
|
2023-12-04 18:26:34 +00:00 |
|
fx_utils.py
|
Make _inductor/fx_utils.py, _dynamo/utils.py pass follow_imports typechecking (#113722)
|
2023-11-16 05:44:15 +00:00 |
|
graph.py
|
Take 2 of "Add an option to log the source of the Triton kernels generated by torch._inductor (#115979)
|
2023-12-18 18:16:44 +00:00 |
|
hooks.py
|
Track exact origin_node on best effort basis (#100110)
|
2023-04-28 04:15:27 +00:00 |
|
index_propagation.py
|
Prefer e.is_number over not e.free_symbols in SymPy (#112688)
|
2023-11-06 20:05:13 +00:00 |
|
inductor_prims.py
|
[BE]: Remove useless lambdas (#113602)
|
2023-11-14 20:06:48 +00:00 |
|
ir.py
|
[AOTI][refactor][3/n] Declare python_kernel_name and cpp_kernel_name in ExternKernel (#115972)
|
2023-12-20 03:22:03 +00:00 |
|
lowering.py
|
Revert "[inductor] Avoid bool being upcast to int (#109913)"
|
2023-12-20 12:33:50 +00:00 |
|
metrics.py
|
metric table (#109245)
|
2023-11-01 02:33:42 +00:00 |
|
optimize_indexing.py
|
Prefer is_number over is_constant() (#114513)
|
2023-12-05 16:56:15 +00:00 |
|
pattern_matcher.py
|
[inductor] Fix shape mismatch in sdpa pattern matcher (#115038)
|
2023-12-03 22:32:12 +00:00 |
|
quantized_lowerings.py
|
[Quant][Inductor] Enable the lowering of quantized maxpool2d (#105906)
|
2023-08-26 08:36:47 +00:00 |
|
scheduler.py
|
[Inductor] Fix constant folding and extern kernel mutation tracking bugs (#115908)
|
2023-12-19 02:06:50 +00:00 |
|
select_algorithm.py
|
[Inductor][Observability] Change to log.debug to avoid excessive long of logs (#115474)
|
2023-12-17 00:25:54 +00:00 |
|
sizevars.py
|
Remove yet more type-ignores in dynamo/inductor (#114684)
|
2023-11-28 22:09:38 +00:00 |
|
test_operators.py
|
Grandfather in some more pytorch ops to be pt2_compliant (#113050)
|
2023-11-09 02:35:33 +00:00 |
|
triton_helpers.py
|
[inductor] Add ir.WelfordReduction with multiple outputs (#104725)
|
2023-08-18 08:18:01 +00:00 |
|
triton_heuristics.py
|
[Triton] Replace triton.runtime.jit.get_cuda_stream with torch.cuda.c… (#115397)
|
2023-12-09 04:30:42 +00:00 |
|
utils.py
|
[AOTI][refactor] Organize model runner files (#116022)
|
2023-12-20 15:35:34 +00:00 |
|
virtualized.py
|
Make V.graph properly typed (#114025)
|
2023-11-21 02:14:29 +00:00 |
|
wrapper_benchmark.py
|
Fix typo under torch/_inductor directory (#110530)
|
2023-10-05 02:17:20 +00:00 |
fe15645619