| .. |
|
autoheuristic
|
PEP585 update - torch/_inductor/[_-i]* (#145137)
|
2025-01-19 01:22:47 +00:00 |
|
codegen
|
[MPSInductor] Add store_reduce method (#150457)
|
2025-04-02 05:12:49 +00:00 |
|
compile_worker
|
Improve subproc autotuning implementation (#149700)
|
2025-03-28 01:06:39 +00:00 |
|
fx_passes
|
[Inductor] Hide reinplace_fsdp_all_gather pass behind skip_fsdp_hooks config (#150436)
|
2025-04-01 22:56:06 +00:00 |
|
kernel
|
[AMD] [TRITON] [INDUCTOR] Add tl.assume to enable bufferops on AMD (#150373)
|
2025-04-01 23:29:39 +00:00 |
|
package
|
[AOTI] Add num_runners to AOTIModelPackageLoader (#149364)
|
2025-03-19 02:28:06 +00:00 |
|
runtime
|
Unify on dynamo_compile as the overall wait counter (#150293)
|
2025-04-01 08:55:51 +00:00 |
|
__autotune_main__.py
|
Improve subproc autotuning implementation (#149700)
|
2025-03-28 01:06:39 +00:00 |
|
__init__.py
|
Fix for AOTI + CUDAGraphs when calling from Python (#148601)
|
2025-03-08 02:44:14 +00:00 |
|
analyze_preserves_zero_mask.py
|
Dont exclude constant_pad_nd in prologue fusion (#149947)
|
2025-03-27 22:26:30 +00:00 |
|
aoti_eager.py
|
PEP585 update - torch/_inductor/[_-i]* (#145137)
|
2025-01-19 01:22:47 +00:00 |
|
async_compile.py
|
Store statically launchable CachingAutotuners inside CompiledFXGraph.triton_bundle (#149054)
|
2025-03-30 17:51:11 +00:00 |
|
autotune_process.py
|
[pytorch][triton] Warp specialization support in TritonTemplate for torchinductor (#148503) (#150122)
|
2025-03-29 03:36:50 +00:00 |
|
bounds.py
|
[inductor] Refactor op handlers part 5 (#146257)
|
2025-02-08 18:00:30 +00:00 |
|
choices.py
|
Reland "Introduce new template heuristic for triton autotune configs" (#147452)
|
2025-03-26 15:47:06 +00:00 |
|
codecache.py
|
Store statically launchable CachingAutotuners inside CompiledFXGraph.triton_bundle (#149054)
|
2025-03-30 17:51:11 +00:00 |
|
comm_analysis.py
|
|
|
|
comm_lowering.py
|
Fix an issue where functional collectives don't force fx stride on inputs when compiled (#146467)
|
2025-02-10 19:15:49 +00:00 |
|
comms.py
|
[BE][PYFMT] migrate PYFMT for torch._inductor to ruff format (#144550)
|
2025-02-28 13:33:19 +00:00 |
|
compile_fx_async.py
|
Use correct boxed_forward_device_index when running CompiledFxGraph.post_compile (#148130)
|
2025-03-23 02:57:58 +00:00 |
|
compile_fx_ext.py
|
async fx compile (#146135)
|
2025-03-19 14:07:51 +00:00 |
|
compile_fx_subproc.py
|
async fx compile (#146135)
|
2025-03-19 14:07:51 +00:00 |
|
compile_fx.py
|
Unify on dynamo_compile as the overall wait counter (#150293)
|
2025-04-01 08:55:51 +00:00 |
|
compiler_bisector.py
|
Add a couple config options to compiler bisector (#148450)
|
2025-03-04 23:23:21 +00:00 |
|
config.py
|
Revert "Enable TMA persistent GEMM Template by default (#149427)"
|
2025-03-31 15:58:34 +00:00 |
|
constant_folding.py
|
skip torchbind in cosntant folding (#148993)
|
2025-03-12 18:08:08 +00:00 |
|
cpp_builder.py
|
[inductor] Fix inductor windows linker error (#150256)
|
2025-04-01 18:30:55 +00:00 |
|
cpu_vec_isa.py
|
Revert "Extend vec backend with BF16 SVE intrinsics (#143666)"
|
2025-03-24 18:13:50 +00:00 |
|
cudagraph_trees.py
|
Cudagraph fix + comment cleanup (#149741)
|
2025-03-21 21:12:36 +00:00 |
|
cudagraph_utils.py
|
[CUDAGraph] Graph Partition (#147648)
|
2025-03-13 16:00:21 +00:00 |
|
custom_graph_pass.py
|
|
|
|
debug.py
|
Fix only logging ir_post_fusion with torch_compile_debug enabled (#148499)
|
2025-03-05 05:35:09 +00:00 |
|
decomposition.py
|
Remove aten.elu core ATen decomp because it is now core ATen (#149780)
|
2025-03-25 01:59:57 +00:00 |
|
dependencies.py
|
[Graph Partition] Support symbol inputs (#149458)
|
2025-03-26 17:21:30 +00:00 |
|
dtype_propagation.py
|
[inductor] Add a helper for convert index_dtype to torch dtype (#149531)
|
2025-03-20 21:33:29 +00:00 |
|
exc.py
|
PEP585 update - torch/_inductor/[_-i]* (#145137)
|
2025-01-19 01:22:47 +00:00 |
|
extern_node_serializer.py
|
PEP585 update - torch/_inductor/[_-i]* (#145137)
|
2025-01-19 01:22:47 +00:00 |
|
freezing_utils.py
|
PEP585: More UP006 fixes (#146392)
|
2025-02-20 06:18:13 +00:00 |
|
freezing.py
|
Fix code cache + freezing compile-time regression (#145868)
|
2025-01-31 02:04:15 +00:00 |
|
fuzzer.py
|
Don't look at TESTING_ONLY in fuzzer (#146870)
|
2025-03-11 05:32:25 +00:00 |
|
fx_utils.py
|
[BE][PYFMT] migrate PYFMT for torch._inductor to ruff format (#144550)
|
2025-02-28 13:33:19 +00:00 |
|
graph.py
|
Move dump location to avoid dumping twice (#150219)
|
2025-03-30 03:35:38 +00:00 |
|
hooks.py
|
PEP585 update - torch/_inductor/[_-i]* (#145137)
|
2025-01-19 01:22:47 +00:00 |
|
index_propagation.py
|
[BE][PYFMT] migrate PYFMT for torch._inductor to ruff format (#144550)
|
2025-02-28 13:33:19 +00:00 |
|
inductor_prims.py
|
[inductor] support dilation in max_pool2d lowering (#148209)
|
2025-03-24 13:00:12 +00:00 |
|
ir.py
|
Dont exclude constant_pad_nd in prologue fusion (#149947)
|
2025-03-27 22:26:30 +00:00 |
|
jagged_lowerings.py
|
PEP585 update - torch/_inductor (#145198)
|
2025-01-21 21:04:33 +00:00 |
|
loop_body.py
|
[inductor] online softmax (#127011)
|
2025-03-06 21:07:18 +00:00 |
|
lowering.py
|
[inductor] No type promotion for slice_scatter (#150090)
|
2025-03-28 17:02:01 +00:00 |
|
memory.py
|
[BE]: Apply ruff PERF403 to use dict comprehensions more often (#149257)
|
2025-03-18 00:46:07 +00:00 |
|
metrics.py
|
[Inductor] Support parallel reduction for GroupNorm (#144020)
|
2025-03-01 17:11:50 +00:00 |
|
mkldnn_ir.py
|
[Inductor][CPP] rename shim_mkldnn.h/.cpp to shim_cpu.h/.cpp (#149372)
|
2025-03-21 03:42:12 +00:00 |
|
mkldnn_lowerings.py
|
[Inductor-CPP] If all of the activation scale dims are 1, make it a 0D tensor (#147033)
|
2025-03-03 18:32:27 +00:00 |
|
mock_cache.py
|
PEP585 update - torch/_inductor (#145198)
|
2025-01-21 21:04:33 +00:00 |
|
ops_handler.py
|
[BE][PYFMT] migrate PYFMT for torch._inductor to ruff format (#144550)
|
2025-02-28 13:33:19 +00:00 |
|
optimize_indexing.py
|
PEP585 update - torch/_inductor (#145198)
|
2025-01-21 21:04:33 +00:00 |
|
output_code.py
|
Store statically launchable CachingAutotuners inside CompiledFXGraph.triton_bundle (#149054)
|
2025-03-30 17:51:11 +00:00 |
|
pattern_matcher.py
|
[inductor]lowering scan to while_loop (#148580)
|
2025-03-20 20:21:02 +00:00 |
|
quantized_lowerings.py
|
Add AOTI shim for _weight_int4pack_mm_cpu_tensor (#149031)
|
2025-03-18 01:33:13 +00:00 |
|
remote_cache.py
|
PEP585 update - torch/_inductor (#145198)
|
2025-01-21 21:04:33 +00:00 |
|
scheduler.py
|
Ignore meta ops in inductor (#150137)
|
2025-03-28 03:01:57 +00:00 |
|
script.ld
|
|
|
|
select_algorithm.py
|
[pytorch][triton] Warp specialization support in TritonTemplate for torchinductor (#148503) (#150122)
|
2025-03-29 03:36:50 +00:00 |
|
sizevars.py
|
[BE][PYFMT] migrate PYFMT for torch._inductor to ruff format (#144550)
|
2025-02-28 13:33:19 +00:00 |
|
subgraph_lowering.py
|
[inductor] Refactor op handlers part 5 (#146257)
|
2025-02-08 18:00:30 +00:00 |
|
template_heuristics.py
|
Reland "Introduce new template heuristic for triton autotune configs" (#147452)
|
2025-03-26 15:47:06 +00:00 |
|
test_case.py
|
[Inductor] be able to disable cache for test (#141195)
|
2025-01-24 19:15:55 +00:00 |
|
test_operators.py
|
|
|
|
triton_bundler.py
|
Store statically launchable CachingAutotuners inside CompiledFXGraph.triton_bundle (#149054)
|
2025-03-30 17:51:11 +00:00 |
|
utils.py
|
Revert "Merge Triton ScaledMM as epilogue to MM template (#150045)"
|
2025-04-01 17:54:28 +00:00 |
|
virtualized.py
|
[inductor] Add a helper for convert index_dtype to torch dtype (#149531)
|
2025-03-20 21:33:29 +00:00 |
|
wrapper_benchmark.py
|
[BE][PYFMT] migrate PYFMT for torch._inductor to ruff format (#144550)
|
2025-02-28 13:33:19 +00:00 |
dee016ceb7