| .. |
|
autoheuristic
|
|
|
|
codegen
|
Make sure not using cpp wrapper when setting nvtx training annotation (#145538)
|
2025-01-30 18:34:22 +00:00 |
|
compile_worker
|
|
|
|
fx_passes
|
[Customized Optimus] Add select cat aten pass (#145918)
|
2025-01-31 02:35:10 +00:00 |
|
kernel
|
Fix a number of flexattention issues (cse, cudagraph, etc.) (#145059)
|
2025-01-29 20:27:39 +00:00 |
|
package
|
|
|
|
runtime
|
[inductor/profiler] add kernel kwargs instrumentation (#145573)
|
2025-01-30 23:51:44 +00:00 |
|
__init__.py
|
|
|
|
analyze_preserves_zero_mask.py
|
|
|
|
aoti_eager.py
|
|
|
|
async_compile.py
|
Parallelize epilogue/prologue benchmarking (#143408)
|
2025-01-28 18:18:24 +00:00 |
|
autotune_process.py
|
|
|
|
bounds.py
|
|
|
|
choices.py
|
|
|
|
codecache.py
|
pickler for GraphModule (#141659)
|
2025-01-31 05:34:28 +00:00 |
|
comm_analysis.py
|
|
|
|
comm_lowering.py
|
|
|
|
comms.py
|
|
|
|
compile_fx.py
|
pickler for GraphModule (#141659)
|
2025-01-31 05:34:28 +00:00 |
|
compiler_bisector.py
|
|
|
|
config.py
|
Turn on fx graph cache and automatic dynamic pgo local caches in fbcode (#146065)
|
2025-01-31 01:11:48 +00:00 |
|
constant_folding.py
|
Fix code cache + freezing compile-time regression (#145868)
|
2025-01-31 02:04:15 +00:00 |
|
cpp_builder.py
|
[AOTI] Remove AOTI_USE_CREATE_TENSOR_FROM_BLOB_V1 (#146039)
|
2025-01-30 19:01:19 +00:00 |
|
cpu_vec_isa.py
|
|
|
|
cudagraph_trees.py
|
|
|
|
cudagraph_utils.py
|
|
|
|
custom_graph_pass.py
|
|
|
|
debug.py
|
add inductor_triton_kernel_mapping_post_grad.json to tlparseadd changes (#145954)
|
2025-01-30 06:18:48 +00:00 |
|
decomposition.py
|
|
|
|
dependencies.py
|
|
|
|
dtype_propagation.py
|
Fix a number of flexattention issues (cse, cudagraph, etc.) (#145059)
|
2025-01-29 20:27:39 +00:00 |
|
exc.py
|
|
|
|
extern_node_serializer.py
|
|
|
|
freezing.py
|
Fix code cache + freezing compile-time regression (#145868)
|
2025-01-31 02:04:15 +00:00 |
|
freezing_utils.py
|
Fix code cache + freezing compile-time regression (#145868)
|
2025-01-31 02:04:15 +00:00 |
|
fuzzer.py
|
|
|
|
fx_utils.py
|
|
|
|
graph.py
|
pickler for GraphModule (#141659)
|
2025-01-31 05:34:28 +00:00 |
|
hooks.py
|
|
|
|
index_propagation.py
|
|
|
|
inductor_prims.py
|
|
|
|
ir.py
|
Record inputs at time of tracing, constrain to them for triton fn (#145448)
|
2025-01-30 16:54:08 +00:00 |
|
jagged_lowerings.py
|
|
|
|
loop_body.py
|
|
|
|
lowering.py
|
Revert "Record inputs at time of tracing, constrain to them for triton fn (#145448)"
|
2025-01-29 18:07:12 +00:00 |
|
memory.py
|
[inductor] Remove type ignores from scheduler.py (#145712)
|
2025-01-28 01:44:32 +00:00 |
|
metrics.py
|
|
|
|
mkldnn_ir.py
|
|
|
|
mkldnn_lowerings.py
|
|
|
|
mock_cache.py
|
|
|
|
ops_handler.py
|
|
|
|
optimize_indexing.py
|
|
|
|
output_code.py
|
pickler for GraphModule (#141659)
|
2025-01-31 05:34:28 +00:00 |
|
pattern_matcher.py
|
|
|
|
quantized_lowerings.py
|
|
|
|
remote_cache.py
|
|
|
|
scheduler.py
|
[BE] Type annotate wrapper_benchmark.py and cuda_combined_scheduling.py (#145542)
|
2025-01-30 03:53:52 +00:00 |
|
script.ld
|
|
|
|
select_algorithm.py
|
Fix a number of flexattention issues (cse, cudagraph, etc.) (#145059)
|
2025-01-29 20:27:39 +00:00 |
|
sizevars.py
|
|
|
|
subgraph_lowering.py
|
|
|
|
test_case.py
|
|
|
|
test_operators.py
|
|
|
|
triton_bundler.py
|
|
|
|
utils.py
|
pickler for GraphModule (#141659)
|
2025-01-31 05:34:28 +00:00 |
|
virtualized.py
|
|
|
|
wrapper_benchmark.py
|
[BE] Type annotate wrapper_benchmark.py and cuda_combined_scheduling.py (#145542)
|
2025-01-30 03:53:52 +00:00 |
