-
Notifications
You must be signed in to change notification settings - Fork 232
Iterative CAGRA-Q #1810
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
irina-resh-nvda
wants to merge
53
commits into
NVIDIA:release/26.10
Choose a base branch
from
irina-resh-nvda:iterative_cagra_q
base: release/26.10
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Iterative CAGRA-Q #1810
Changes from all commits
Commits
Show all changes
53 commits
Select commit
Hold shift + click to select a range
23aed4e
chore(cagra): drop local dev artifacts (.clangd, .gitignore entries)
irina-resh-nvda a4ebee6
feat(cagra): add batched_device_view_from_host utility and unit test
irina-resh-nvda 90fcf80
fix(cagra): bound random seed selection to graph size during build
irina-resh-nvda 4bf8a16
feat(cagra): iterative CAGRA-Q graph build with configurable in-build…
irina-resh-nvda 90d1219
feat(bench): expose iterative CAGRA-Q build/search params in cuvs_bench
irina-resh-nvda a938958
test(cagra): VPQ/iterative build test updates
irina-resh-nvda 4f4068a
fix(cagra): use in-place gather for dataset shuffle (remove raft work…
irina-resh-nvda c804088
Merge branch 'main' into iterative_cagra_q
irina-resh-nvda 278a4f3
Merge branch 'main' into iterative_cagra_q
aamijar cc65291
fix style
aamijar 25e6d7d
restore clangd and gitignore changes
aamijar 6bca275
revert cuvs_bench warning
aamijar 6ed4ab5
remove whitespace
aamijar 9d44b23
remove duplicate file in cmakelists.txt
aamijar 73c9bbc
revert to auto for type deduction
aamijar 23cf815
remove commented out code
aamijar c2f9b6a
fix(cagra): pass graph_size to persistent single-CTA kernel to bound …
irina-resh-nvda cad2e8f
Brought back the tests
irina-resh-nvda 0e98b34
Fixed the test
irina-resh-nvda 8a378cb
Removed dataset shuffle
irina-resh-nvda aa2227b
Removed unused pointer residency helper; use memory_type_from_pointer…
irina-resh-nvda d9c6bfd
Pre-commit changes
irina-resh-nvda ae89f9f
perf(cagra): per-batch VPQ query reconstruction + device-pool graph t…
irina-resh-nvda 355d240
Revert "Pre-commit changes"
aamijar 8cd4191
revert another spdx change
aamijar 6ad9234
revert test to minimize diff
aamijar adf364f
Merge main and fix merge conflicts
aamijar 8a9fda5
remove unrelated utility and test
aamijar befe09c
PQ dataset API
aamijar 492d765
remove alias
aamijar dc2ccfe
remove unused operators
aamijar 79bd7bb
remove some small diff
aamijar bb1fcde
VPQ dataset serialization so CAGRA-Q can build from a compressed data…
irina-resh-nvda 31c6322
Recognise a compressed .vpq base_file in the ann benchmark and hand i…
irina-resh-nvda 843425b
Don't refuse a compressed base set in search mode: cuvs_cagra's needs…
irina-resh-nvda 689a882
Serialize the VPQ dataset with a CAGRA-Q index so a loaded index sear…
irina-resh-nvda 8863d1d
C and Python APIs
aamijar 10c7e1f
Merge branch 'main' into iterative_cagra_q
aamijar e47bbca
Merge remote-tracking branch 'origin/iterative_cagra_q' into iterativ…
irina-resh-nvda 28ca46b
Reverse cuvsbench changes
irina-resh-nvda 682ee36
Share the iterative CAGRA build query chunk size as a constant
irina-resh-nvda b3c551f
Don't count graph staging buffers in optimize_workspace_size when the…
irina-resh-nvda c030c57
Model the iterative CAGRA build's peak host and device memory, includ…
irina-resh-nvda f4790ca
added tests for memory estimation
irina-resh-nvda 7d9db3b
merge main and fix conflicts
aamijar 6cc01fd
rename
tarang-jain c45f76d
pre-allocate buffers
tarang-jain 4f5e9eb
try using strided queries
tarang-jain 66b82ed
Merge NVIDIA release/26.10 into iterative_cagra_q.
tarang-jain bdc1b84
bring graph to device
tarang-jain ec4bc35
Drop iterative CAGRA-Q ann-bench param parsing from this branch.
tarang-jain 70180eb
more review changes
tarang-jain 3166185
Merge branch 'release/26.10' into iterative_cagra_q
tarang-jain File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
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
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
Oops, something went wrong.
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This function compresses the dataset into VPQ format. The user can decide later to use that for CAGRA, or for other algorithms. It would make sense to rename the params struct to something like
cuvsPqParams.