13f15b38fc
Support consolidating sharded checkpoints with the `fabric` CLI ( #19560 )
2024-03-04 08:01:33 -05:00
d9113b61cc
Add additional references in compile guides ( #19550 )
2024-03-04 08:00:50 -05:00
34f036917d
Document `ddp_find_unused_parameters_true` in Fabric ( #19564 )
2024-03-04 06:10:38 -05:00
48c39ce24f
Compile guide for Trainer ( #19531 )
...
Co-authored-by: Luca Antiga <luca.antiga@gmail.com>
2024-02-28 09:15:33 -05:00
abae4c903b
Update Lightning AI multi-node guide (Trainer) ( #19530 )
...
* update
* update
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* configure_model
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-02-28 08:35:53 -05:00
ea89133c65
Rename `fabric run model` to `fabric run` ( #19527 )
2024-02-27 11:36:46 -05:00
e461e90f84
Update the Multi-GPU docs ( #19525 )
2024-02-26 22:29:26 -05:00
cf3553cdb5
docs: enable Sphinx linter & fixing ( #19515 )
...
* docs: enable Sphinx linter
* fixes
2024-02-26 16:20:33 +01:00
e43820a4be
migrate Data subpackage ( #19523 )
...
* update
* update
* update
* update
* Update checkgroup.yml
* More
* Add note
* Labeller should be kept as long as we have the stubs
* update
* update
* update
* Apply suggestions from code review
* init
* ci fix
* pin version range
* https://www.neptune.ai/
---------
Co-authored-by: Carlos Mocholí <carlossmocholi@gmail.com>
Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
Co-authored-by: Jirka <jirka.borovec@seznam.cz>
2024-02-26 08:25:00 -05:00
2a827f3f6f
Docs fixes ( #19529 )
2024-02-26 12:06:08 +01:00
623ec5824f
`load_from_checkpoint` support for LightningCLI when using dependency injection ( #18105 )
2024-02-23 10:55:07 +01:00
c5ab34876b
Document optional steps for converting Fabric code ( #19486 )
2024-02-18 00:37:35 +01:00
5998dd12e8
docs: ignore mall behave link ( #19488 )
2024-02-16 17:48:51 +01:00
61ba180e5f
docs: Bump HPU ref `1.4.0` ( #19484 )
...
Co-authored-by: jerome-habana <jerome-habana@users.noreply.github.com>
Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
2024-02-16 16:28:16 +01:00
120c87f8f7
Include the training mode in the ModelSummary ( #19468 )
2024-02-15 15:13:35 -05:00
59e45d6f6d
Update `all_gather` docs ( #19469 )
2024-02-14 19:37:50 +01:00
4bcc4f1cf7
Document the return value of `Fabric.clip_gradients()` ( #19457 )
2024-02-13 11:32:47 +01:00
0a77aa2cc5
Some clarifications in the torch.compile Fabric docs ( #19456 )
2024-02-13 06:52:29 +01:00
e950bb4828
Remove the Graphcore IPU integration ( #19405 )
...
Co-authored-by: Carlos Mocholí <carlossmocholi@gmail.com>
2024-02-12 16:16:02 -05:00
2ed7282f7c
Rename Lightning Fabric CLI ( #19442 )
...
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
2024-02-12 17:22:53 +01:00
0acd5f9810
Rename Lightning App CLI ( #19440 )
2024-02-09 16:54:54 +01:00
9c8cd4ce68
Update to 2.3.0dev ( #19430 )
...
Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
2024-02-08 06:34:51 -05:00
db2cc8a88e
Fix CLI docs typo ( #19426 )
2024-02-07 10:53:58 -05:00
78b7a39e72
Update throughput docs ( #19415 )
2024-02-06 16:26:10 -05:00
130b05fe0c
Fix dead link in docs ( #19387 )
2024-02-06 11:54:17 +01:00
9624aae07e
Support non-strict loading in Trainer ( #19404 )
2024-02-05 19:57:43 -05:00
89ff87def0
Reapply compile in `Fabric.setup()` by default ( #19382 )
2024-02-01 15:06:18 -05:00
509b2ca560
Docs: fix FSDP acronym ( #19384 )
2024-02-01 16:02:59 +01:00
c346f4d159
Compile guide for Fabric ( #19330 )
2024-01-31 14:57:07 -05:00
6421dd8d4f
precommit: drop Black in favor of Ruff ( #19380 )
2024-01-31 17:09:39 +00:00
1a59097ab2
Drop support for PyTorch 1.12 ( #19300 )
...
Co-authored-by: Carlos Mocholí <carlossmocholi@gmail.com>
Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
2024-01-26 11:44:24 -05:00
7cc79fe7ba
Reapply `torch.compile` in Fabric.setup() ( #19280 )
2024-01-23 21:17:41 -05:00
1faddcb24c
Update Lightning AI multi-node guide ( #19324 )
...
Co-authored-by: Luca Antiga <luca.antiga@gmail.com>
2024-01-23 18:23:49 -05:00
b1127e3608
Utility to consolidate sharded checkpoints ( #19213 )
...
Co-authored-by: Carlos Mocholí <carlossmocholi@gmail.com>
2024-01-23 17:15:22 -05:00
93c1ab0653
Dedicated docs page for distributed checkpoints (Trainer) ( #19299 )
2024-01-17 12:20:12 +01:00
a4ecf8d5c8
Dedicated docs page for distributed checkpoints ( #19287 )
2024-01-16 08:44:10 -05:00
1bd27447d9
Fix typo in `log_graph` docs ( #19254 )
2024-01-10 19:00:27 +01:00
a1dd9efcf7
Drop XLA XRT support ( #19232 )
...
* Drop XLA XRT support
* update test
* set launched
* update conftest
* xla available check
---------
Co-authored-by: awaelchli <aedu.waelchli@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-01-10 18:39:20 +01:00
79b082a2ba
docs: fix link to colossalai ( #19263 )
2024-01-10 18:11:27 +01:00
f62e312185
docs: update references to ext. integrations ( #19248 )
...
* drop stale projects
* hpu 1.3.0
* copy & index
* prune
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-01-09 13:12:53 +01:00
97469c600f
TransformerEngine fallback compute dtype ( #19082 )
...
Co-authored-by: Adrian Wälchli <aedu.waelchli@gmail.com>
2023-12-14 03:02:09 +01:00
e769e233aa
ci: build app's docs with RTFD ( #19147 )
...
* ci: build app's docs with RTFD
* set -ex
* .[app]
2023-12-13 07:37:36 +01:00
7fee4ae3a6
docs: fix broken link awesome-panel ( #19140 )
2023-12-12 09:39:47 +00:00
4af5ec0d34
docs: drop legacy links ( #19116 )
2023-12-05 19:02:02 +01:00
7d04de697e
Reorder `configure_model` ( #19060 )
2023-12-05 02:29:32 +01:00
c5363af1c2
Fix the "our" word duplication in the docs ( #19055 )
...
There were a bit inconsistent sentences with
a word duplication issue in the documentation.
These changes also:
* unify references to the Compatibility matrix
* add a reference to the Compatibility matrix
into PyTorch Lightning's Installation Docs
2023-12-01 11:28:29 -05:00
294db45294
Fix missing module alias in Trainer reference ( #19089 )
2023-12-01 10:58:39 -05:00
9d366046b9
Clarify requirements for `Trainer.fit(ckpt_path="last")` ( #19066 )
2023-11-27 11:03:45 -05:00
b79b68481e
Clarify setup of optimizer when using `empty_init=True` ( #19067 )
2023-11-26 11:04:36 +01:00
90043798e4
Clarify `self.log(..., rank_zero_only=True|False)` ( #19056 )
...
Co-authored-by: Carlos Mocholí <carlossmocholi@gmail.com>
2023-11-23 13:02:21 -05:00
awaelchli