remove uneccesarry field for FixedBlockPool in inference (#5729)#5729
Closed
hy-NJU wants to merge 1 commit intopytorch:mainfrom
Closed
remove uneccesarry field for FixedBlockPool in inference (#5729)#5729hy-NJU wants to merge 1 commit intopytorch:mainfrom
hy-NJU wants to merge 1 commit intopytorch:mainfrom
Conversation
Contributor
hy-NJU
pushed a commit
to hy-NJU/FBGEMM
that referenced
this pull request
May 4, 2026
Summary: X-link: facebookresearch/FBGEMM#2657 In the training FixedBlockPool, we have 4 field: int64_t key; uint32_t timestamp; uint32_t count : 31 bool used : 1; But count field is never used in inference while take 4 bytes DRAM space. Here we set up InferenceFixedBlockPool to save such space Reviewed By: emlin Differential Revision: D91654624
meta-codesync
Bot
changed the title
hy-NJU
pushed a commit
to hy-NJU/FBGEMM
that referenced
this pull request
May 5, 2026
Summary: X-link: facebookresearch/FBGEMM#2657 In the training FixedBlockPool, we have 4 field: int64_t key; uint32_t timestamp; uint32_t count : 31 bool used : 1; But count field is never used in inference while take 4 bytes DRAM space. Here we set up InferenceFixedBlockPool to save such space Reviewed By: emlin Differential Revision: D91654624
hy-NJU
pushed a commit
to hy-NJU/FBGEMM
that referenced
this pull request
May 5, 2026
Summary: X-link: facebookresearch/FBGEMM#2657 In the training FixedBlockPool, we have 4 field: int64_t key; uint32_t timestamp; uint32_t count : 31 bool used : 1; But count field is never used in inference while take 4 bytes DRAM space. Here we set up InferenceFixedBlockPool to save such space Reviewed By: emlin Differential Revision: D91654624
Summary: X-link: facebookresearch/FBGEMM#2657 In the training FixedBlockPool, we have 4 field: int64_t key; uint32_t timestamp; uint32_t count : 31 bool used : 1; But count field is never used in inference while take 4 bytes DRAM space. Here we set up InferenceFixedBlockPool to save such space Reviewed By: emlin Differential Revision: D91654624
hy-NJU
pushed a commit
to hy-NJU/FBGEMM
that referenced
this pull request
May 5, 2026
Summary: X-link: facebookresearch/FBGEMM#2657 In the training FixedBlockPool, we have 4 field: int64_t key; uint32_t timestamp; uint32_t count : 31 bool used : 1; But count field is never used in inference while take 4 bytes DRAM space. Here we set up InferenceFixedBlockPool to save such space Reviewed By: emlin Differential Revision: D91654624
Contributor
|
This pull request has been merged in 4ad11ec. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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:
X-link: https://github.com/facebookresearch/FBGEMM/pull/2657
In the training FixedBlockPool, we have 4 field:
int64_t key;
uint32_t timestamp;
uint32_t count : 31
bool used : 1;
But count field is never used in inference while take 4 bytes DRAM space.
Here we set up InferenceFixedBlockPool to save such space
Reviewed By: emlin
Differential Revision: D91654624