-
Notifications
You must be signed in to change notification settings - Fork 63
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
Branch 24.12 merge 24.10 #407
Merged
AyodeAwe
merged 12 commits into
rapidsai:branch-24.12
from
benfred:branch-24.12-merge-24.10
Oct 10, 2024
Merged
Branch 24.12 merge 24.10 #407
AyodeAwe
merged 12 commits into
rapidsai:branch-24.12
from
benfred:branch-24.12-merge-24.10
Oct 10, 2024
Conversation
This file contains 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
rapidsai#380) This PR fixes rapidsai#375. Authors: - Tamas Bela Feher (https://github.com/tfeher) Approvers: - Corey J. Nolet (https://github.com/cjnolet) URL: rapidsai#380
For the cuml integration, we need to be able to statically link to cuvs in order build the python wheels. This change adds a static target that lets us do that Authors: - Ben Frederickson (https://github.com/benfred) Approvers: - Corey J. Nolet (https://github.com/cjnolet) URL: rapidsai#382
This PR implements a distributed (single-node-multiple-GPUs) implementation of ANN indexes. It allows to build, extend and search an index on multiple GPUs. Before building the index, the user has to choose between two modes : **Sharding mode** : The index dataset is split, each GPU trains its own index with its respective share of the dataset. This is intended to both increase the search throughput and the maximal size of the index. **Index duplication mode** : The index is built once on a GPU and then copied over to others. Alternatively, the index dataset is sent to each GPU to be built there. This intended to increase the search throughput. SNMG indexes can be serialized and de-serialized. Local models can also be deserialized and deployed in index duplication mode. ![bench](https://github.com/user-attachments/assets/e313d0ef-02eb-482a-9104-9e1bb400456d) Migrated from rapidsai/raft#1993 Authors: - Victor Lafargue (https://github.com/viclafargue) - James Lamb (https://github.com/jameslamb) - Corey J. Nolet (https://github.com/cjnolet) Approvers: - Tamas Bela Feher (https://github.com/tfeher) - James Lamb (https://github.com/jameslamb) - Corey J. Nolet (https://github.com/cjnolet) URL: rapidsai#231
Seeing build errors in the cuml wheels, and the only difference afaict was adding the cuvs-cagra-search to link to the static library. Removing this since cuml is the only consumer of the static library this release and doesn't use cagra (will revisit in 24.12)
Authors: - Divye Gala (https://github.com/divyegala) - Corey J. Nolet (https://github.com/cjnolet) Approvers: - Corey J. Nolet (https://github.com/cjnolet) URL: rapidsai#246
Adding documentation for each index type. This decouples the major details in the docs from the individual language API docs to present users with a better overal experience. The major topcs in the new index-level docs are meant to be more exhaustive than the API docs in providing 1. Description of each index type, when it's useful and shortcomings 2. Links to any relevant research material to learn more foundational info 3. Hyper-parameters 4. Links to API docs for each supported language 5. Links to example projects and notebooks 6. Formulas for rough estimates of memory footprint 7. How to use in cuvs-bench, along with some rough benchmarks on different hardware --------- Co-authored-by: Micka <[email protected]>
Authors: - Tarang Jain (https://github.com/tarang-jain) Approvers: - Corey J. Nolet (https://github.com/cjnolet) - Micka (https://github.com/lowener) URL: rapidsai#346
Builds upon rapidsai#367 Authors: - Divye Gala (https://github.com/divyegala) - Dante Gama Dessavre (https://github.com/dantegd) - Corey J. Nolet (https://github.com/cjnolet) Approvers: - Corey J. Nolet (https://github.com/cjnolet) - Bradley Dice (https://github.com/bdice) URL: rapidsai#368
Authors: - Ben Frederickson (https://github.com/benfred) Approvers: - Corey J. Nolet (https://github.com/cjnolet) URL: rapidsai#395
This PR adds some critical doc fixes for 24.10- 1. Since we're working on the Nvidia developer landing page for cuVS, our README content needs to be aligned. 2. The cuvs-bench documentation was missing the datasets guide and table of contents. 3. The cuvs-bench docs weren't linked into the main docs. 4. cuvs-bench was missing several of the mg enabled algorithms, their constraints, and parameter ranges. --------- Co-authored-by: Micka <[email protected]> Co-authored-by: viclafargue <[email protected]>
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.
No description provided.