| .. |
|
codegen
|
[inductor] Fix AOTInductor (#99203)
|
2023-04-25 14:42:12 +00:00 |
|
fx_passes
|
inductor: fix issue for conv+binary issue for binary scalar path (#99860)
|
2023-04-25 06:25:14 +00:00 |
|
kernel
|
[inductor] Consolidate constant_args and cpp_constant_args (#98742)
|
2023-04-12 11:59:08 +00:00 |
|
__init__.py
|
[inductor] Fix AOTInductor (#99203)
|
2023-04-25 14:42:12 +00:00 |
|
autotune_process.py
|
[inductor][easy] create a wrap for triton do_bench function (#99216)
|
2023-04-18 00:52:00 +00:00 |
|
codecache.py
|
[inductor] Fix AOTInductor (#99203)
|
2023-04-25 14:42:12 +00:00 |
|
compile_fx.py
|
[inductor] Fix AOTInductor (#99203)
|
2023-04-25 14:42:12 +00:00 |
|
config.py
|
Add pattern to normalize split (#99588)
|
2023-04-22 01:08:11 +00:00 |
|
coordinate_descent_tuner.py
|
[reland][inductor] coordinate descent tuning upon max-autotune (#99594)
|
2023-04-20 19:55:52 +00:00 |
|
cuda_properties.py
|
|
|
|
cudagraph_trees.py
|
Make autocast cache and buffer stealing aware of cudagraph static output tensors (#99368)
|
2023-04-24 20:23:12 +00:00 |
|
debug.py
|
tweak heuristic for sdpa selection based off of *data* (and a decision tree) (#99644)
|
2023-04-21 23:28:44 +00:00 |
|
decomposition.py
|
[inductor] Fix shape padding (#99917)
|
2023-04-25 13:40:29 +00:00 |
|
dependencies.py
|
Fix typos under torch/_inductor directory (#97592)
|
2023-04-10 22:53:18 +00:00 |
|
exc.py
|
|
|
|
fx_utils.py
|
|
|
|
graph.py
|
[inductor] Fix AOTInductor (#99203)
|
2023-04-25 14:42:12 +00:00 |
|
ir.py
|
[inductor] Fix AOTInductor (#99203)
|
2023-04-25 14:42:12 +00:00 |
|
lowering.py
|
[inductor] Lower aten.prod (#99484)
|
2023-04-24 02:48:27 +00:00 |
|
metrics.py
|
|
|
|
mkldnn.py
|
inductor: fix onednn conv2d(transpose) packed issue when input size is three (#99601)
|
2023-04-21 04:32:35 +00:00 |
|
optimize_indexing.py
|
|
|
|
overrides.py
|
[Inductor] Fix rand_like with kwargs device of str type (#99673)
|
2023-04-21 20:33:14 +00:00 |
|
pattern_matcher.py
|
Add support for call_method patterns (#99782)
|
2023-04-24 19:26:26 +00:00 |
|
scheduler.py
|
Unbreak torch.compile on macos (#99119)
|
2023-04-14 15:30:27 +00:00 |
|
select_algorithm.py
|
torch._int_mm: fix triton kernel caching (#99283)
|
2023-04-18 22:07:02 +00:00 |
|
sizevars.py
|
simplify indexing expression before trying to determine strides (#98783)
|
2023-04-11 20:01:20 +00:00 |
|
test_operators.py
|
|
|
|
triton_heuristics.py
|
[ROCM] Do not send "debug"=True down to triton.compile (#99756)
|
2023-04-25 08:08:05 +00:00 |
|
utils.py
|
[Inductor] Fix rand_like with kwargs device of str type (#99673)
|
2023-04-21 20:33:14 +00:00 |
|
virtualized.py
|
Add device_asserts before indirect loads and stores (#98590)
|
2023-04-19 21:26:57 +00:00 |
e43918b93a