strisunshinewentingwang/pytorch

Pull Requests Commits

[vision hash update] update the pinned vision hash (#121177)

pytorchupdatebot committed 188 days ago

f0b9a834

[FSDP] Avoided CPU sync in `clip_grad_norm_` (#122001)

awgu committed 188 days ago

b9469170

[mergebot][BE] If we don't have any required checks, don't run required checks (#121921)

PaliC committed 188 days ago

7bc91d5d

Don't use Proxy torch function in the sym size calls (#121981)

soulitzer committed 188 days ago

2b71b21a

Document complex optimizer semantic behavior (#121667)

janeyx99 committed 188 days ago

37e56327

[inductor] FX graph cache: Fix bug handling constants (#121925)

masnesral committed 188 days ago

12662900

[Clang-tidy header][25/N] Fix clang-tidy warnings and enable clang-tidy on c10/cuda/*.{cpp,h} (#121952)

cyyever committed 188 days ago

6b0f6189

Revert "Fix torch.clamp in MPS to handle NaN correctly (#121381)"

pytorchmergebot committed 188 days ago

0cc60a05

Revert "Force upsample to be float32 (#121324)"

pytorchmergebot committed 188 days ago

07ec3356

[docs] Added comment on replicate -> partial for `_NormPartial` (#121976)

awgu committed 188 days ago

256c0ec1

Revert "[BE] Enables support for pytorch ci build in ARC + introduces _linux-build-rg.yml. (#121930)"

pytorchmergebot committed 188 days ago

b717aa6f

Fix torch.clamp in MPS to handle NaN correctly (#121381)

lamroger committed 188 days ago

ca80d07a

[c10d] initialize lastEnqueuedSeq_ and lastCompletedSeq_ (#121980)

shuqiangzhang committed 188 days ago

26aaabb9

format caffe2/torch/_export/serde/serialize.py (#121670)

strisunshinewentingwang committed 188 days ago

dfc5e932

Update get_aten_graph_module (#121937)

tugsbayasgalan committed 188 days ago

53d2188d

[Doc][NVTX] Add documentation for nvtx.range (#121699)

Aidyn-A committed 188 days ago

af86d67d

[DTensor] Enable ASGD foreach optimizer and add the associated unit test (#121942)

wz337 committed 188 days ago

b92daff6

[DTensor] Supported 2D `clip_grad_norm_` (#121945)

awgu committed 188 days ago

f4dd2fda

[BE] Enables support for pytorch ci build in ARC + introduces _linux-build-rg.yml. (#121930)

jeanschmidt committed 188 days ago

2c33e3a3

[inductor] FX graph cache: simplify "current callable" logic (#121903)

masnesral committed 188 days ago

6f4fa8e9

Fix torch.compile links (#121824)

lezcano committed 188 days ago

d0d09f59

Move doc links to point to main (#121823)

lezcano committed 188 days ago

8a5a3771

Enable FX graph caching in another batch of inductor tests (#121697)

masnesral committed 188 days ago

535bc71d

Fall back to eager mode when viewing with differing bitwidths (#120998) (#121786)

tfiala committed 188 days ago

3ee319c4

Add lowering for cummax, cummin (#120429)

isuruf committed 188 days ago

409b1a60

[dynamo][compile-time] Remove preserve rng state per op (#121923)

anijain2305 committed 188 days ago

d04faf45

Fix FakeTensorUpdater logic for updating fake tensors (#116168)

isuruf committed 188 days ago

67ec8702

combine loops so fn_name correct in error message (#121601)

drewd789 committed 188 days ago

239d87af

[release] Increase version 2.3.0->2.4.0 (#121974)

atalman committed 188 days ago

39fdde7f

update kineto submodule commit id (#121843)

shengbao-zheng committed 188 days ago

565d1e28

Newer Older