Swap IntNBit TBE Kernel with SSD Embedding DB TBE Kernel for SSD Infernece Enablement #3134
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
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D76953960 |
faran928
force-pushed
the
export-D76953960
branch
from
63aadbb to
76fce37
Compare
faran928
added a commit
to faran928/torchrec
that referenced
this pull request
Jun 24, 2025
…rnece Enablement (pytorch#3134) Summary: For SSD inference, we have added EmbeddingDB as a custom in house storage not exposed to OSS. We leverage TGIF stack to rewrite IntNBit TBE Kernel with SSD EmbeddingDB TBE kernel as SSD TBE embedding kernel can't be exposed within TorchRec code base. Additionally, for SSD we only provide in di_sharding_pass and SSD can be enabled without having additional DI shards. In that case, for the tables that assigned to CPU host we can just do tw sharding of those tables. Added the TW sharding logic accordingly. Differential Revision: D76953960
|
This pull request was exported from Phabricator. Differential Revision: D76953960 |
faran928
added a commit
to faran928/torchrec
that referenced
this pull request
Jun 24, 2025
…rnece Enablement (pytorch#3134) Summary: For SSD inference, we have added EmbeddingDB as a custom in house storage not exposed to OSS. We leverage TGIF stack to rewrite IntNBit TBE Kernel with SSD EmbeddingDB TBE kernel as SSD TBE embedding kernel can't be exposed within TorchRec code base. Additionally, for SSD we only provide in di_sharding_pass and SSD can be enabled without having additional DI shards. In that case, for the tables that assigned to CPU host we can just do tw sharding of those tables. Added the TW sharding logic accordingly. Differential Revision: D76953960
faran928
force-pushed
the
export-D76953960
branch
from
76fce37 to
bf3b57a
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76953960 |
jingsh
suggested changes
Jun 24, 2025
| @@ -224,6 +224,7 @@ def __init__( | |||
| self._is_weighted: bool = module.is_weighted() | |||
| self._lookups: List[nn.Module] = [] | |||
| self._create_lookups(fused_params, device) | |||
| self._fused_params = fused_params | |||
There was a problem hiding this comment.
Suggested change
| self._fused_params = fused_params | |
| self.fused_params = fused_params |
looks like this attr is used externally, remove the _
faran928
added a commit
to faran928/torchrec
that referenced
this pull request
Jun 24, 2025
…rnece Enablement (pytorch#3134) Summary: For SSD inference, we have added EmbeddingDB as a custom in house storage not exposed to OSS. We leverage TGIF stack to rewrite IntNBit TBE Kernel with SSD EmbeddingDB TBE kernel as SSD TBE embedding kernel can't be exposed within TorchRec code base. Additionally, for SSD we only provide in di_sharding_pass and SSD can be enabled without having additional DI shards. In that case, for the tables that assigned to CPU host we can just do tw sharding of those tables. Added the TW sharding logic accordingly. Differential Revision: D76953960
faran928
force-pushed
the
export-D76953960
branch
from
bf3b57a to
dfe6abf
Compare
…rnece Enablement (pytorch#3134) Summary: Pull Request resolved: pytorch#3134 For SSD inference, we have added EmbeddingDB as a custom in house storage not exposed to OSS. We leverage TGIF stack to rewrite IntNBit TBE Kernel with SSD EmbeddingDB TBE kernel as SSD TBE embedding kernel can't be exposed within TorchRec code base. Additionally, for SSD we only provide in di_sharding_pass and SSD can be enabled without having additional DI shards. In that case, for the tables that assigned to CPU host we can just do tw sharding of those tables. Added the TW sharding logic accordingly. Differential Revision: D76953960
|
This pull request was exported from Phabricator. Differential Revision: D76953960 |
faran928
force-pushed
the
export-D76953960
branch
from
dfe6abf to
415e11e
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary:
For SSD inference, we have added EmbeddingDB as a custom in house storage not exposed to OSS. We leverage TGIF stack to rewrite IntNBit TBE Kernel with SSD EmbeddingDB TBE kernel as SSD TBE embedding kernel can't be exposed within TorchRec code base.
Additionally, for SSD we only provide in di_sharding_pass and SSD can be enabled without having additional DI shards. In that case, for the tables that assigned to CPU host we can just do tw sharding of those tables. Added the TW sharding logic accordingly.
Differential Revision: D76953960