Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
7,120 Commits 32 Branches 59 Tags
master
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Jiaming Yuan 9ecb7583e9 [EM] Add basic distributed GPU tests. (#10861) 
- Split Hist and Approx tests in unittests.
- Basic GPU tests for distributed.
 2024-10-01 01:28:43 +08:00
Jiaming Yuan 92f1c48a22 [EM] Get quantile cuts from the extmem qdm. (#10860) 2024-10-01 00:59:28 +08:00
Jiaming Yuan 8cf2f7aed8 [CI] Set timeout for freebsd vm launch. (#10858) 2024-09-30 18:26:27 +08:00
Jiaming Yuan c9f89c4241 [R] Rename ExternalDMatrix -> ExtMemDMatrix. (#10849) 2024-09-29 05:45:53 +08:00
Jiaming Yuan 271f4a80e7 Use CUDA virtual memory for pinned memory allocation. (#10850) 
- Add a grow-only virtual memory allocator.
- Define a driver API wrapper. Split up the runtime API wrapper.
 2024-09-28 04:26:44 +08:00
Jiaming Yuan 13b9874fd6 [jvm-packages] Bump rapids version. (#10857) 2024-09-28 04:02:24 +08:00
Jiaming Yuan cc2daadec3 Fix git ignore. [skip ci] (#10854) 2024-09-28 01:43:29 +08:00
Jiaming Yuan bc69a3e877 [EM] Improve memory estimation for quantile sketching. (#10843) 
I- Add basic estimation for RMM.
- Re-estimate after every sub-batch.
- Some debug logs for memory usage.
- Fix the locking mechanism in the memory allocator logger.
 2024-09-25 03:20:09 +08:00
Jiaming Yuan 68a8865bc5 [CI] Fix PyLint errors. (#10837) 2024-09-24 14:09:32 +08:00
Jiaming Yuan e228c1a121 [EM] Make page concatenation optional. (#10826) 
This PR introduces a new parameter `extmem_concat_pages` to make the page concatenation optional for GPU hist. In addition, the document is updated for the new GPU-based external memory.
 2024-09-24 06:19:28 +08:00
Jiaming Yuan 2a37a8880c Check correct dump format for gblinear. (#10831) 2024-09-21 00:32:52 +08:00
Jiaming Yuan 24241ed6e3 [EM] Compress dense ellpack. (#10821) 
This helps reduce the memory copying needed for dense data. In addition, it helps reduce memory usage even if external memory is not used.

- Decouple the number of symbols needed in the compressor with the number of features when the data is dense.
- Remove the fetch call in the `at_end_` iteration.
- Reduce synchronization and kernel launches by using the `uvector` and ctx.
 2024-09-20 18:20:56 +08:00
Jiaming Yuan d5e1c41b69 [coll] Use loky for rabit op tests. (#10828) 2024-09-20 16:46:05 +08:00
Jiaming Yuan 96bbf80457 [EM] Suport quantile objectives for GPU-based external memory. (#10820) 
- Improved error message for memory usage.
- Support quantile-based objectives for GPU external memory.
 2024-09-17 13:27:02 +08:00
Jiaming Yuan d94f6679fc [EM] Avoid synchronous calls and unnecessary ATS access. (#10811) 
- Pass context into various functions.
- Factor out some CUDA algorithms.
- Use ATS only for update position.
 2024-09-10 14:33:14 +08:00
Jiaming Yuan ed5f33df16 [EM] Multi-level quantile sketching for GPU. (#10813) 2024-09-10 13:08:34 +08:00
Jiaming YuanandCorentin Santos 3ef8383d93 [doc] Fix custom_metric_obj.rst [skip ci] (#10796) (#10815) 
Added the square to the derivative in the hessian

Co-authored-by: Corentin Santos <corentin.santos@iphc.cnrs.fr>
 2024-09-10 05:11:43 +08:00
Jiaming Yuan 5f7f31d464 [EM] Refactor ellpack construction. (#10810) 
- Remove the calculation of n_symbols in the accessor.
- Pack initialization steps into the parameter list.
- Pass the context into various ctors.
- Specialization for dense data to prepare for further compression.
 2024-09-09 14:10:10 +08:00
Jiaming Yuan e1a2c1bbb3 [EM] Merge GPU partitioning with histogram building. (#10766) 
- Stop concatenating pages if there's no subsampling.
- Use a single iteration for histogram build and partitioning.
 2024-08-31 03:25:37 +08:00
Jiaming Yuan 98ac153265 Avoid warning from NVCC. (#10757) 2024-08-30 16:11:31 +08:00
Jiaming YuanandPhilip Hyunsu Cho 5cc7c735e5 Don't link gputreeshap. (#10758) 
Co-authored-by: Philip Hyunsu Cho <chohyu01@cs.washington.edu>
 2024-08-30 14:40:58 +08:00
Jiaming Yuan 34d4ab455e [EM] Avoid stream sync in quantile sketching. (#10765) 
.
 2024-08-30 12:33:24 +08:00
Jiaming Yuan 61dd854a52 [EM] Refactor GPU histogram builder. (#10764) 
- Expose the maximum number of cached nodes to be consistent with the CPU implementation. Also easier for testing.
- Extract the subtraction trick for easier testing.
- Split up the `GradientQuantiser` to avoid circular dependency.
 2024-08-30 02:39:14 +08:00
Jiaming Yuan 34937fea41 [EM] Python wrapper for the ExtMemQuantileDMatrix. (#10762) 
Not exposed to the document yet.

- Add C API.
- Add Python API.
- Basic CPU tests.
 2024-08-29 04:08:25 +08:00
Jiaming Yuan 7510a87466 [EM] Reuse the quantile container. (#10761) 
Use the push method to merge the quantiles instead of creating multiple containers. This
reduces the memory usage by consistent pruning.
 2024-08-29 01:39:55 +08:00
Jiaming Yuan 4fe67f10b4 [EM] Have one partitioner for each batch. (#10760) 
- Initialize one partitioner for each batch.
- Collect partition size during initialization.
- Support base ridx in the finalization.
 2024-08-29 01:35:17 +08:00
Jiaming Yuan 64afe9873b Increase timeout in C++ tests from 1 to 5 seconds. (#10756) 
To avoid CI failures on FreeBSD.
 2024-08-28 02:27:14 +08:00
Jiaming Yuan bde1265caf [EM] Return a full DMatrix instead of a Ellpack from the GPU sampler. (#10753) 2024-08-28 01:05:11 +08:00
Jiaming Yuan d6ebcfb032 [EM] Support CPU quantile objective for external memory. (#10751) 2024-08-27 04:16:57 +08:00
Jiaming Yuan 06c4246ff1 [CI] Workaround mypy errors. (#10754) 2024-08-27 02:54:11 +08:00
Jiaming Yuan 25966e4ba8 [EM] Pass batch parameter into extmem format. (#10736) 
- Allow customization for format reading.
- Customize the number of pre-fetch batches.
 2024-08-27 02:37:50 +08:00
Jiaming Yuan fd0138c91c [coll] Improve column split tests with named threads. (#10735) 2024-08-24 12:43:47 +08:00
Jiaming Yuan 55aef8f546 [EM] Avoid resizing host cache. (#10734) 
* [EM] Avoid resizing host cache.

- Add SAM allocator and resource.
- Use page-based cache instead of stream-based cache.
 2024-08-23 06:34:01 +08:00
Jiaming Yuan 142bdc73ec [EM] Support SHAP contribution with QDM. (#10724) 
- Add GPU support.
- Add external memory support.
- Update the GPU tree shap.
 2024-08-22 05:25:10 +08:00
Jiaming Yuan cb54374550 Update clang-tidy. (#10730) 
- Install cmake using pip.
- Fix compile command generation.
- Clean up the tidy script and remove the need to load the yaml file.
- Fix modernized type traits.
- Fix span class. Polymorphism support is dropped
 2024-08-22 04:12:18 +08:00
Jiaming Yuan 9b88495840 [multi] Implement weight feature importance. (#10700) 2024-08-22 02:06:47 +08:00
Jiaming Yuan 402e7837fb Fix potential race in feature constraint. (#10719) 2024-08-21 16:50:31 +08:00
Jiaming Yuan 508ac13243 Check cub errors. (#10721) 
- Make sure cuda error returned by cub scan is caught.
- Avoid temporary buffer allocation in thrust device vector.
 2024-08-21 02:50:26 +08:00
Jiaming Yuan fd365c147e [doc] Brief note about RMM SAM allocator. [skip ci] (#10712) 2024-08-17 04:21:39 +08:00
Jiaming Yuan ec3f327c20 Add managed memory allocator. (#10711) 2024-08-17 03:02:34 +08:00
Jiaming Yuan 8d7fe262d9 [EM] Enable access to the number of batches. (#10691) 
- Expose `NumBatches` in `DMatrix`.
- Small cleanup for removing legacy CUDA stream and ~force CUDA context initialization~.
- Purge old external memory data generation code.
 2024-08-17 02:59:45 +08:00
Jiaming Yuan 033a666900 [EM] Log the page size of ellpack. (#10713) 2024-08-17 01:35:47 +08:00
Jiaming Yuan abe65e3769 Reduce thread contention in column split histogram test. (#10708) 2024-08-17 01:00:32 +08:00
Jiaming Yuan 2258bc870d Add more tests and doc for QDM. (#10692) 2024-08-16 23:30:04 +08:00
Jiaming Yuan 582ea104b5 [EM] Enable prediction cache for GPU. (#10707) 
- Use `UpdatePosition` for all nodes and skip `FinalizePosition` when external memory is used.
- Create `encode/decode` for node position, this is just as a refactor.
- Reuse code between update position and finalization.
 2024-08-15 21:41:59 +08:00
Jiaming Yuan 2ecc85ffad [EM] Support ExtMemQdm in the GPU predictor. (#10694) 2024-08-13 12:21:11 +08:00
Jiaming Yuan 43704549a2 [coll] Reduce the amount of open files (socket). (#10693) 
Reduce the chance of hitting `Failed to call `socket`: Too many open files`.
 2024-08-13 05:23:49 +08:00
Jiaming Yuan d414fdf2e7 [EM] Add GPU version of the external memory QDM. (#10689) 2024-08-10 10:49:43 +08:00
Jiaming Yuan 7bccc1ea2c [EM] CPU implementation for external memory QDM. (#10682) 
- A new DMatrix type.
- Extract common code into a new QDM base class.

Not yet working:
- Not exposed to the interface yet, will wait for the GPU implementation.
- ~No meta info yet, still working on the source.~
- Exporting data to CSR is not supported yet.
 2024-08-09 09:38:02 +08:00
Jiaming Yuan cc3b56fc37 Cleanup GPU Hist tests. (#10677) 
* Cleanup GPU Hist tests.

- Remove GPU Hist gradient sampling test. The same properties are tested in the gradient
  sampler test suite.
- Move basic histogram tests into the histogram test suite.
- Remove the header inclusion of the `updater_gpu_hist.cu` in tests.
 2024-08-06 11:50:44 +08:00
Jiaming Yuan 6ccf116601 [dask] Reduce the flakiness of tests. (#10678) 2024-08-06 06:04:10 +08:00
Jiaming Yuan 3d8107adb8 Support doc link for the sklearn module. (#10287) 2024-08-06 02:35:32 +08:00
Jiaming Yuan a269055b2b [coll] Use loky for tests. (#10676) 
This makes the tests easier to run and debug. In addition, they can now work on Windows as
well.
 2024-08-03 07:33:42 +08:00
Jiaming Yuan a185b693dc Reduce warnings and flakiness in tests. (#10659) 
- Fix warnings in tests.
- Try to reduce the flakiness of dask test.
 2024-08-03 07:32:47 +08:00
Jiaming Yuan 2e7ba900ef [CI] Add timeout limit to JVM tests. (#10673) 2024-08-03 01:51:13 +08:00
Jiaming Yuan 574c20dc1d Enable CI build for the federated-secure branch. (#10671) 2024-08-02 22:13:17 +08:00
Jiaming YuanandPhilip Hyunsu Cho 77c844cef7 Reduce thread contention in column split tests. (#10658) 
---------

Co-authored-by: Philip Hyunsu Cho <chohyu01@cs.washington.edu>
 2024-08-01 18:36:46 +08:00
Jiaming YuanandHyunsu Cho fb77ed7603 [CI] Fix Python wheel workflow. (#10649) 
* [CI] Fix Python wheel workflow.

* Use Python 3.10 for building wheels

---------

Co-authored-by: Hyunsu Cho <phcho@nvidia.com>
 2024-07-30 10:13:47 -07:00
Jiaming Yuan 827d0e8edb [breaking] Bump Python requirement to 3.10. (#10434) 
- Bump the Python requirement.
- Fix type hints.
- Use loky to avoid deadlock.
- Workaround cupy-numpy compatibility issue on Windows caused by the `safe` casting rule.
- Simplify the repartitioning logic to avoid dask errors.
 2024-07-30 17:31:06 +08:00
Jiaming Yuan 449be7a402 Quick fix for clang-tidy error. (#10641) 2024-07-26 18:21:16 +08:00
Jiaming Yuan fcae6301ec [dask] Disable broadcast in the scatter call. (#10632) 2024-07-25 04:16:34 +08:00
Jiaming Yuan 485d90218c Catch exceptions during file read. (#10623) 2024-07-23 03:48:19 +08:00
Jiaming Yuan a19bbc9be5 Avoid caching allocator for large allocations. (#10582) 2024-07-23 03:48:03 +08:00
Jiaming Yuan b2cae34a8e Fix integer overflow. (#10615) 2024-07-23 02:13:15 +08:00
Jiaming Yuan 6d9fcb771e Move device histogram storage into histogram.cuh. (#10608) 2024-07-21 14:10:13 +08:00
Jiaming Yuan cb62f9e73b [EM] Prevent init with CUDA malloc resource. (#10606) 2024-07-21 05:08:29 +08:00
Jiaming Yuan 0846ad860c Optionally skip cupy on windows. (#10611) 2024-07-20 22:12:12 +08:00
Jiaming Yuan 344ddeb9ca Drop support for CUDA legacy stream. (#10607) 2024-07-20 06:14:56 +08:00
Jiaming Yuan 7ab93f3ce3 [CI] Fix test environment. (#10609) 
* [CI] Fix test environment.

* Remove shell.

* Remove.

* Update Dockerfile.i386
 2024-07-18 10:04:17 -07:00
Jiaming Yuan 292bb677e5 [EM] Support mmap backed ellpack. (#10602) 
- Support resource view in ellpack.
- Define the CUDA version of MMAP resource.
- Define the CUDA version of malloc resource.
- Refactor cuda runtime API wrappers, and add memory access related wrappers.
- gather windows macros into a single header.
 2024-07-18 08:20:21 +08:00
Jiaming Yuan e9fbce9791 Refactor DeviceUVector. (#10595) 
Create a wrapper instead of using inheritance to avoid inconsistent interface of the class.
 2024-07-18 03:33:01 +08:00
Jiaming Yuan a6a8a55ffa Merge approx tests. (#10583) 2024-07-16 19:03:48 +08:00
Jiaming Yuan 5a92ffe3ca Partial fix for CTK 12.5 (#10574) 2024-07-16 17:41:50 +08:00
Jiaming Yuan bbd308595a [jvm-packages] Bump rapids version. (#10588) 2024-07-15 20:21:25 +08:00
Jiaming Yuan 5fea9d24f2 Small cleanup for CMake scripts. (#10573) 
- Remove rabit.
 2024-07-12 05:18:23 +08:00
Jiaming Yuan 6c403187ec Fix column split race condition. (#10572) 2024-07-12 01:07:12 +08:00
Jiaming Yuan 1ca4bfd20e Avoid thrust vector initialization. (#10544) 
* Avoid thrust vector initialization.

- Add a wrapper for rmm device uvector.
- Split up the `Resize` method for HDV.
 2024-07-11 17:29:27 +08:00
Jiaming Yuan 89da9f9741 [fed] Split up federated test CMake file. (#10566) 
- Collect all federated test files into the same directory.
- Independently list the files.
 2024-07-11 13:09:18 +08:00
Jiaming Yuan 5f910cd4ff [EM] Handle base idx in GPU histogram. (#10549) 2024-07-11 03:26:30 +08:00
Jiaming Yuan 34b154c284 Avoid the use of size_t in the partitioner. (#10541) 
- Avoid the use of size_t in the partitioner.
- Use `Span` instead of `Elem` where `node_id` is not needed.
- Remove the `const_cast`.
- Make sure the constness is not removed in the `Elem` by making it reference only.

size_t is implementation-defined, which causes issue when we want to pass pointer or span.
 2024-07-11 00:43:08 +08:00
Jiaming Yuan baba3e9eb0 Fix empty partition. (#10559) 2024-07-10 13:01:47 +08:00
Jiaming Yuan 8e2b874b4c [doc] Add notes about RMM and device ordinal. [skip ci] (#10562) 
- Remove the experimental tag, we have been running it for a long time now.
- Add notes about avoiding set CUDA device.
- Add link in parameter.
 2024-07-10 13:00:57 +08:00
Jiaming Yuan 3ec74a1ba9 [doc] Add build_info to autodoc. [skip ci] (#10551) 2024-07-10 04:05:20 +08:00
Jiaming Yuan 2266db17d1 [R] Update roxygen. (#10556) 2024-07-08 17:02:46 +08:00
Jiaming Yuan 00264eb72b [EM] Basic distributed test for external memory. (#10492) 2024-07-06 01:15:20 +08:00
Jiaming Yuan 620b2b155a Cache GPU histogram kernel configuration. (#10538) 2024-07-04 15:38:59 +08:00
Jiaming Yuan cd1d108c7d [doc] Fix learning to rank tutorial. [skip ci] (#10539) 2024-07-03 22:52:26 +08:00
Jiaming Yuan 6243e7c43d [doc] Update link to release notes. [skip ci] (#10533) 2024-07-03 12:16:53 +08:00
Jiaming Yuan 628411a654 Enhance the threadpool implementation. (#10531) 
- Accept an initialization function.
- Support void return tasks.
 2024-07-03 12:13:27 +08:00
Jiaming Yuan 9cb4c938da [EM] Move prefetch in reset into the end of the iteration. (#10529) 2024-07-03 03:48:18 +08:00
Jiaming Yuan e537b0969f Fix boolean array for arrow-backed DF. (#10527) 2024-07-02 17:02:54 +08:00
Jiaming Yuan d33043a348 [coll] Allow using local host for testing. (#10526) 
- Don't try to retrieve the IP address if a host is specified.
- Fix compiler deprecation warning.
 2024-07-02 15:34:38 +08:00
Jiaming Yuan a39fef2c67 [fed] Fixes for the encrypted GRPC backend. (#10503) 2024-07-02 15:15:12 +08:00
Jiaming Yuan 5f0c1e902b Small cleanup for error message. (#10502) 
- The `Fail` function can handle file location automatically.
- Report concatenated error for connection poll.
- Typos.
 2024-07-02 13:36:41 +08:00
Jiaming Yuan e8a962575a [EM] Allow staging ellpack on host for GPU external memory. (#10488) 
- New parameter `on_host`.
- Abstract format creation and stream creation into policy classes.
 2024-06-28 04:42:18 +08:00
Jiaming Yuan 824fba783e Remove support for deprecated format in Python. (#10490) 2024-06-27 11:31:53 +08:00
Jiaming Yuan 2d88d17008 Remove deprecated DeviceQuantileDMatrix. (#10491) 2024-06-27 11:30:51 +08:00
Jiaming Yuan 26eb68859f Consistently report error in tests. (#10453) 2024-06-21 14:35:22 +08:00
Jiaming Yuan b38c7fe2ce 2.1.0 release news.(#10378) 2024-06-21 14:34:53 +08:00
Jiaming Yuan 2b400b18d5 Small cleanup for rowset collection. (#10401) 2024-06-19 18:06:23 +08:00