| .. |
|
autoheuristic
|
[BE][Ez]: Optimize unnecessary lambda with operator (#154722)
|
2025-05-30 23:47:10 +00:00 |
|
codegen
|
[Inductor][CPU] Use AMX-based microkernels when M > 4 for GEMM template for INT4 weight (#155444)
|
2025-06-12 02:28:48 +00:00 |
|
compile_worker
|
torch.compile: Supress stdout / stderr output from subprocesses when local (#153837)
|
2025-05-22 05:49:43 +00:00 |
|
fx_passes
|
[inductor] handle -1 for pointless view pairs (#155295)
|
2025-06-11 22:20:36 +00:00 |
|
kernel
|
unify symbolic_shapes and sizevars dynamic shapes APIs naming 1 (#154774)
|
2025-06-12 16:11:55 +00:00 |
|
package
|
[export] Refactor pt2 save/load (#152495)
|
2025-06-04 06:04:29 +00:00 |
|
runtime
|
Migrate from lru_cache to cache (#155613)
|
2025-06-11 19:44:18 +00:00 |
|
__autotune_main__.py
|
|
|
|
__init__.py
|
Add optional device index to AOTIModelPackageLoader (#152093)
|
2025-05-04 11:40:12 +00:00 |
|
analyze_preserves_zero_mask.py
|
|
|
|
aoti_eager.py
|
|
|
|
async_compile.py
|
Redo D75092426: [internal] Expose additional metadata to compilation callbacks (#155063)
|
2025-06-05 23:40:31 +00:00 |
|
autotune_process.py
|
Migrate from lru_cache to cache (#155613)
|
2025-06-11 19:44:18 +00:00 |
|
bounds.py
|
|
|
|
choices.py
|
|
|
|
codecache.py
|
[cutlass backend] Only consider to use re worker if nvcc doesn't exist (#155745)
|
2025-06-12 15:23:52 +00:00 |
|
comm_analysis.py
|
|
|
|
comm_lowering.py
|
Revert "[inductor] Add typing to _inductor/ir.py (#149958)"
|
2025-06-06 15:19:16 +00:00 |
|
comms.py
|
[PT2][comms] put visualize_overlap in a try-except block (#155222)
|
2025-06-05 23:39:48 +00:00 |
|
compile_fx_async.py
|
|
|
|
compile_fx_ext.py
|
Migrate from lru_cache to cache (#155613)
|
2025-06-11 19:44:18 +00:00 |
|
compile_fx_subproc.py
|
|
|
|
compile_fx.py
|
[inductor][invoke_subgraph] Mark invoke_subgraph outputs as user_visible to constrain output strides (#155395)
|
2025-06-12 03:58:16 +00:00 |
|
compiler_bisector.py
|
Migrate from lru_cache to cache (#155613)
|
2025-06-11 19:44:18 +00:00 |
|
config.py
|
inductor codecache: include private inductor configs in cache key (#153672)
|
2025-06-11 01:33:24 +00:00 |
|
constant_folding.py
|
Add dont constant fold flag (#154945)
|
2025-06-10 14:52:26 +00:00 |
|
cpp_builder.py
|
Migrate from lru_cache to cache (#155613)
|
2025-06-11 19:44:18 +00:00 |
|
cpu_vec_isa.py
|
Migrate from lru_cache to cache (#155613)
|
2025-06-11 19:44:18 +00:00 |
|
cudagraph_trees.py
|
Redo D75092426: [internal] Expose additional metadata to compilation callbacks (#155063)
|
2025-06-05 23:40:31 +00:00 |
|
cudagraph_utils.py
|
|
|
|
custom_graph_pass.py
|
Revert "Custom FX pass for inductor's backend registration (#154841)"
|
2025-06-09 16:56:45 +00:00 |
|
debug.py
|
[inductor][cutlass backend] Log prescreening elpase (#155508)
|
2025-06-12 16:48:52 +00:00 |
|
decomposition.py
|
Migrate from lru_cache to cache (#155613)
|
2025-06-11 19:44:18 +00:00 |
|
dependencies.py
|
Revert "[inductor] Add typing to _inductor/ir.py (#149958)"
|
2025-06-06 15:19:16 +00:00 |
|
dtype_propagation.py
|
Migrate from lru_cache to cache (#155613)
|
2025-06-11 19:44:18 +00:00 |
|
exc.py
|
|
|
|
extern_node_serializer.py
|
|
|
|
freezing_utils.py
|
|
|
|
freezing.py
|
[cudagraphs] Fix issue in collecting static_input_idxs (#152287)
|
2025-04-30 03:24:05 +00:00 |
|
fuzzer.py
|
[AOTI][reland] Add an option to specify custom op C shim (#153968)
|
2025-05-21 15:57:57 +00:00 |
|
fx_utils.py
|
Revert "Inductor logging + analysis of torch.profile (#149697)"
|
2025-06-10 15:38:40 +00:00 |
|
graph.py
|
Update auto-tuning support for _scaled_grouped_mm (#150944)
|
2025-06-11 19:12:52 +00:00 |
|
hooks.py
|
|
|
|
index_propagation.py
|
unify symbolic_shapes and sizevars dynamic shapes APIs naming 1 (#154774)
|
2025-06-12 16:11:55 +00:00 |
|
inductor_prims.py
|
[inductor] lowering for fractional_max_pool3d (#148630)
|
2025-05-22 16:06:29 +00:00 |
|
ir.py
|
unify symbolic_shapes and sizevars dynamic shapes APIs naming 1 (#154774)
|
2025-06-12 16:11:55 +00:00 |
|
jagged_lowerings.py
|
Revert "[inductor] Add typing to _inductor/ir.py (#149958)"
|
2025-06-06 15:19:16 +00:00 |
|
loop_body.py
|
Migrate from lru_cache to cache (#155613)
|
2025-06-11 19:44:18 +00:00 |
|
lowering.py
|
Migrate from lru_cache to cache (#155613)
|
2025-06-11 19:44:18 +00:00 |
|
memory.py
|
[PT2][memory] correct wait tensor output size (#153569)
|
2025-06-04 17:49:25 +00:00 |
|
metrics.py
|
Replace runtime type parameterization (#155221)
|
2025-06-05 21:43:54 +00:00 |
|
mkldnn_ir.py
|
Revert "[Inductor] Improve typing, and prepare for ABI-compatible AOTI C-shim dispatching (#154371)"
|
2025-06-08 17:37:29 +00:00 |
|
mkldnn_lowerings.py
|
Revert "[inductor] Add typing to _inductor/ir.py (#149958)"
|
2025-06-06 15:19:16 +00:00 |
|
mock_cache.py
|
|
|
|
ops_handler.py
|
Revert "[inductor] Add typing to _inductor/ir.py (#149958)"
|
2025-06-06 15:19:16 +00:00 |
|
optimize_indexing.py
|
|
|
|
output_code.py
|
Reflect back mutation if we clone misaligned tensors (#154442)
|
2025-05-29 13:36:48 +00:00 |
|
pattern_matcher.py
|
Migrate from lru_cache to cache (#155613)
|
2025-06-11 19:44:18 +00:00 |
|
quantized_lowerings.py
|
[Inductor]Cleanup autotune_fallback_to_aten post-deprecation (#154331)
|
2025-05-29 20:29:58 +00:00 |
|
remote_cache.py
|
[Indcutor Remote Cache] Raise an exception if redis module is required but not available (#151779)
|
2025-04-26 11:21:54 +00:00 |
|
scheduler.py
|
Revert "Inductor logging + analysis of torch.profile (#149697)"
|
2025-06-10 15:38:40 +00:00 |
|
script.ld
|
|
|
|
select_algorithm.py
|
[inductor][cutlass backend] Log prescreening elpase (#155508)
|
2025-06-12 16:48:52 +00:00 |
|
sizevars.py
|
unify symbolic_shapes and sizevars dynamic shapes APIs naming 1 (#154774)
|
2025-06-12 16:11:55 +00:00 |
|
standalone_compile.py
|
Add logging for guard miss failure (#153125)
|
2025-05-09 16:51:04 +00:00 |
|
subgraph_lowering.py
|
|
|
|
template_heuristics.py
|
[Inductor] Add Additional Configs for persistent+TMA version of Triton mm and addmm (#150587)
|
2025-04-23 18:21:35 +00:00 |
|
test_case.py
|
|
|
|
test_operators.py
|
|
|
|
tiling_utils.py
|
Turn on new tiling by default (#154768)
|
2025-06-06 21:19:35 +00:00 |
|
triton_bundler.py
|
Keep raw cubin file around in case it gets deleted underneath us (#153064)
|
2025-05-08 14:29:19 +00:00 |
|
utils.py
|
unify symbolic_shapes and sizevars dynamic shapes APIs naming 1 (#154774)
|
2025-06-12 16:11:55 +00:00 |
|
virtualized.py
|
|
|
|
wrapper_benchmark.py
|
Revert "Inductor logging + analysis of torch.profile (#149697)"
|
2025-06-10 15:38:40 +00:00 |
6c0b42fd2f