[dtensor][4/N] have row-wise sharding always use LocalShardsWrapper #122843
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/122843
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit cc5525a with merge base e70bf23 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
pytorch-bot
bot
added
ciflow/inductor
oncall: distributed
wanchaol
reviewed
Apr 4, 2024
…dsWrapper"
**Summary**
Always wrap local tensor into a `LocalShardsWrapper`. This is for uniformity and it leads to easiness on adoption of DTensor as a wrapper for local shard(s) representation. To support more tensor ops over `LocalShardsWrapper`, users need to extend its `__torch_dispatch__`.
**Test**
`torchrun --standalone --nnodes=1 --nproc-per-node=4 torch/distributed/_tensor/examples/torchrec_sharding_example.py -e row-wise-even`
**Result**
```
Row-wise even sharding example in DTensor
Col 0-15
------- ----------
Row 0-1 cuda:0
Row 2-3 cuda:1
Row 4-5 cuda:2
Row 6-7 cuda:3
```
cc mrshenli pritamdamania87 zhaojuanmao satgera rohan-varma gqchen aazzolini osalpekar jiayisuse H-Huang kwen2501 awgu penguinwu fegin wanchaol fduwjj wz337 tianyu-l wconstab yf225 chauhang
[ghstack-poisoned]
pytorchmergebot
pushed a commit
that referenced
this pull request
Apr 16, 2024
…ticipating ranks only (#122853) **Summary** We wrap DTensor's local tensor in `LocalShardsWrapper` for torchrec's table-wise sharding. The exception is on non-participating ranks: for non-participating ranks, the local tensor is an empty torch.Tensor object. The reason of this design is to avoid complexity on supporting empty tensor case on `LocalShardsWrapper`. **Test** `torchrun --standalone --nnodes=1 --nproc-per-node=4 torch/distributed/_tensor/examples/torchrec_sharding_example.py -e table-wise` Pull Request resolved: #122853 Approved by: https://github.com/wz337 ghstack dependencies: #120265, #121392, #122843
sanketpurandare
pushed a commit
to sanketpurandare/pytorch
that referenced
this pull request
Apr 22, 2024
…ytorch#122843) **Summary** Always wrap local tensor into a `LocalShardsWrapper`. This is for uniformity and it leads to easiness on adoption of DTensor as a wrapper for local shard(s) representation. To support more tensor ops over `LocalShardsWrapper`, users need to extend its `__torch_dispatch__`. **Test** `torchrun --standalone --nnodes=1 --nproc-per-node=4 torch/distributed/_tensor/examples/torchrec_sharding_example.py -e row-wise-even` **Result** ``` Row-wise even sharding example in DTensor Col 0-15 ------- ---------- Row 0-1 cuda:0 Row 2-3 cuda:1 Row 4-5 cuda:2 Row 6-7 cuda:3 ``` Pull Request resolved: pytorch#122843 Approved by: https://github.com/wz337 ghstack dependencies: pytorch#120265, pytorch#121392
sanketpurandare
pushed a commit
to sanketpurandare/pytorch
that referenced
this pull request
Apr 22, 2024
…ticipating ranks only (pytorch#122853) **Summary** We wrap DTensor's local tensor in `LocalShardsWrapper` for torchrec's table-wise sharding. The exception is on non-participating ranks: for non-participating ranks, the local tensor is an empty torch.Tensor object. The reason of this design is to avoid complexity on supporting empty tensor case on `LocalShardsWrapper`. **Test** `torchrun --standalone --nnodes=1 --nproc-per-node=4 torch/distributed/_tensor/examples/torchrec_sharding_example.py -e table-wise` Pull Request resolved: pytorch#122853 Approved by: https://github.com/wz337 ghstack dependencies: pytorch#120265, pytorch#121392, pytorch#122843
petrex
pushed a commit
to petrex/pytorch
that referenced
this pull request
May 3, 2024
…ytorch#122843) **Summary** Always wrap local tensor into a `LocalShardsWrapper`. This is for uniformity and it leads to easiness on adoption of DTensor as a wrapper for local shard(s) representation. To support more tensor ops over `LocalShardsWrapper`, users need to extend its `__torch_dispatch__`. **Test** `torchrun --standalone --nnodes=1 --nproc-per-node=4 torch/distributed/_tensor/examples/torchrec_sharding_example.py -e row-wise-even` **Result** ``` Row-wise even sharding example in DTensor Col 0-15 ------- ---------- Row 0-1 cuda:0 Row 2-3 cuda:1 Row 4-5 cuda:2 Row 6-7 cuda:3 ``` Pull Request resolved: pytorch#122843 Approved by: https://github.com/wz337 ghstack dependencies: pytorch#120265, pytorch#121392
petrex
pushed a commit
to petrex/pytorch
that referenced
this pull request
May 3, 2024
…ticipating ranks only (pytorch#122853) **Summary** We wrap DTensor's local tensor in `LocalShardsWrapper` for torchrec's table-wise sharding. The exception is on non-participating ranks: for non-participating ranks, the local tensor is an empty torch.Tensor object. The reason of this design is to avoid complexity on supporting empty tensor case on `LocalShardsWrapper`. **Test** `torchrun --standalone --nnodes=1 --nproc-per-node=4 torch/distributed/_tensor/examples/torchrec_sharding_example.py -e table-wise` Pull Request resolved: pytorch#122853 Approved by: https://github.com/wz337 ghstack dependencies: pytorch#120265, pytorch#121392, pytorch#122843
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Stack from ghstack (oldest at bottom):
Summary
Always wrap local tensor into a
LocalShardsWrapper. This is for uniformity and it leads to easiness on adoption of DTensor as a wrapper for local shard(s) representation. To support more tensor ops overLocalShardsWrapper, users need to extend its__torch_dispatch__.Test
torchrun --standalone --nnodes=1 --nproc-per-node=4 torch/distributed/_tensor/examples/torchrec_sharding_example.py -e row-wise-evenResult
cc @mrshenli @pritamdamania87 @zhaojuanmao @satgera @rohan-varma @gqchen @aazzolini @osalpekar @jiayisuse @H-Huang @kwen2501 @awgu @penguinwu @fegin @wanchaol @fduwjj @wz337 @tianyu-l @wconstab @yf225 @chauhang