Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
829 commits
Select commit Hold shift + click to select a range
1e5fa03
Attempt to address oom failures in test suite (#1672)
wence- Sep 9, 2024
687ed5c
[FEA] Allow setting `*_pool_size` with human-readable string (#1670)
Matt711 Sep 9, 2024
6729def
Update RMM adaptors, containers and tests to use get/set_current_devi…
harrism Sep 9, 2024
800dc87
Add missing include to `resource_ref.hpp` (#1677)
miscco Sep 10, 2024
68a51d3
Recommend `miniforge` for conda install. (#1681)
bdice Sep 18, 2024
58039d3
Use CI workflow branch 'branch-24.10' again [skip ci] (#1683)
jameslamb Sep 18, 2024
f4ec463
DOC v24.12 Updates [skip ci]
raydouglass Sep 19, 2024
99e237e
Update fmt (to 11.0.2) and spdlog (to 1.14.1). (#1678)
jameslamb Sep 23, 2024
1823321
Merge pull request #1684 from rapidsai/branch-24.10
GPUtester Sep 23, 2024
ab6e296
update update-version.sh to use packaging lib (#1685)
AyodeAwe Sep 24, 2024
163db70
Merge pull request #1686 from rapidsai/branch-24.10
GPUtester Sep 24, 2024
b514473
exclude 'gcovr' from list of development pip packages (#1688)
jameslamb Sep 27, 2024
9e410c0
Use `rmm::percent_of_free_device_memory` in arena test (#1689)
wence- Sep 30, 2024
6489bb7
[Improvement] Reorganize Cython to separate C++ bindings and make Cyt…
Matt711 Oct 3, 2024
8150032
Fix `rmm ._lib` imports (#1693)
Matt711 Oct 4, 2024
c494395
Prune workflows based on changed files (#1695)
KyleFromNVIDIA Oct 4, 2024
afe0a33
Update Changelog [skip ci]
raydouglass Oct 9, 2024
a381645
Merge pull request #1700 from rapidsai/branch-24.10
GPUtester Oct 9, 2024
4e519bb
Update cross-link to cuda-python object (#1699)
wence- Oct 9, 2024
69a297d
Add BUILD_SHARED_LIBS option defaulting to ON (#1702)
wence- Oct 9, 2024
f715518
make conda installs in CI stricter (#1696)
jameslamb Oct 9, 2024
90a5631
Fix typos in .gitignore (#1697)
charlesbluca Oct 9, 2024
1b70ffd
make conda installs in CI stricter (part 2) (#1703)
jameslamb Oct 11, 2024
de42f57
Deprecate support for directly accessing logger (#1690)
vyasr Oct 16, 2024
50e60a8
Fix docs warning (#1706)
bdice Oct 16, 2024
1024a12
Update rmm tests to use rapids_cmake_support_conda_env (#1707)
robertmaynard Oct 22, 2024
1ebfe0a
devcontainer: replace `VAULT_HOST` with `AWS_ROLE_ARN` (#1708)
jjacobelli Oct 25, 2024
47dae24
print sccache stats in builds (#1712)
jameslamb Oct 29, 2024
8d49fff
Deprecate `rmm._lib` (#1713)
Matt711 Oct 31, 2024
9b76d36
Correct rmm tests for validity of device pointers (#1714)
robertmaynard Nov 1, 2024
dbae8c0
[fea] Expose the arena mr to the Python interface. (#1711)
trivialfis Nov 1, 2024
d4c0635
Disallow cuda-python 12.6.1 and 11.8.4 (#1720)
bdice Nov 6, 2024
a98c22a
WIP: put a ceiling on cuda-python (#1723)
jameslamb Nov 7, 2024
771ccdc
use rapids-generate-pip-constraints to pin to oldest dependencies in …
jameslamb Nov 7, 2024
56f3a46
enforce wheel size limits, README formatting in CI (#1726)
jameslamb Nov 13, 2024
220003e
Treat deprecation warnings as errors and fix deprecation warnings in …
harrism Nov 14, 2024
52d61c5
Remove all explicit usage of fmtlib (#1724)
harrism Nov 14, 2024
c7fc017
adding telemetry (#1692)
msarahan Nov 14, 2024
96418d3
DOC v25.02 Updates [skip ci]
raydouglass Nov 15, 2024
929a595
Make `cudaMallocAsync` logic non-optional as we require CUDA 11.2+ (#…
robertmaynard Nov 19, 2024
b33ebf9
Merge pull request #1732 from rapidsai/branch-24.12
GPUtester Nov 19, 2024
3b5f6af
Query total memory in failure_callback_resource_adaptor tests (#1734)
harrism Nov 20, 2024
d54a28a
Merge pull request #1735 from rapidsai/branch-24.12
GPUtester Nov 20, 2024
4cfa31f
Create logger wrapper around spdlog that can be easily reused in othe…
vyasr Nov 26, 2024
c9c6039
Add breaking change workflow trigger (#1719)
AyodeAwe Nov 26, 2024
a6a455d
Require approval to run CI on draft PRs (#1737)
bdice Nov 26, 2024
f9b9f84
Use consistent signature for target_link_libraries (#1738)
vyasr Nov 26, 2024
d4066fa
Fix some logger issues (#1739)
vyasr Nov 27, 2024
00287e0
Remove upper bounds on cuda-python to allow 12.6.2 and 11.8.5 (#1729)
bdice Dec 5, 2024
9b0e71d
Revise README. (#1747)
bdice Dec 6, 2024
e0e4517
Update build.sh (#1749)
vyasr Dec 6, 2024
fc9c138
Update cuda-python lower bounds to 12.6.2 / 11.8.5 (#1751)
bdice Dec 7, 2024
83a8971
Adds fabric handle and memory protection flags to cuda_async_memory_r…
abellina Dec 7, 2024
09f7f62
Add configuration for pre-commit.ci, update pre-commit hooks (#1746)
bdice Dec 9, 2024
ff59ea4
stop installing 'wheel' in wheel-building script (#1748)
jameslamb Dec 9, 2024
8d41610
Remove memory access flags from cuda_async_memory_resource (#1754)
abellina Dec 9, 2024
46b232e
gate telemetry dispatch calls on TELEMETRY_ENABLED env var (#1752)
msarahan Dec 9, 2024
c3841dd
Use bindings layout for all cuda-python imports. (#1756)
bdice Dec 10, 2024
73a66c9
fix version references (skip ci) (#1757)
AyodeAwe Dec 10, 2024
b391ce8
Update Changelog [skip ci]
raydouglass Dec 11, 2024
3cad8fe
Use ruff, remove isort and black. (#1759)
bdice Dec 11, 2024
9adaf07
Merge branch 'branch-24.12' into branch-25.02-merge-24.12
bdice Dec 14, 2024
9aff755
Merge branch-24.12 into branch-25.02
bdice Dec 14, 2024
bf606ef
Remove `rmm._lib` (#1765)
Matt711 Dec 14, 2024
c7798bd
Merge pull request #1766 from bdice/branch-25.02-merge-24.12
raydouglass Dec 16, 2024
a83c2ea
Remove ignored cuda-python deprecation warning. (#1768)
bdice Dec 17, 2024
c7c38fa
Fix codespell behavior. (#1769)
bdice Dec 17, 2024
65858a9
Remove deprecated factory functions from resource adaptors. (#1767)
bdice Dec 17, 2024
1af03eb
remove certs and simplify telemetry summarize (#1750)
msarahan Dec 17, 2024
3bf6026
Add missing array header include (#1771)
robertmaynard Dec 19, 2024
ba35f8e
Reduce dependencies on numba. (#1761)
bdice Dec 20, 2024
8275ba8
Switch to using separate rapids-logger repo (#1774)
vyasr Jan 2, 2025
0a8e920
Check if nightlies have succeeded recently enough (#1772)
vyasr Jan 3, 2025
b4c43c5
Use rapids-cmake for the logger (#1776)
vyasr Jan 3, 2025
d70bd4b
[pre-commit.ci] pre-commit autoupdate (#1778)
pre-commit-ci[bot] Jan 7, 2025
c1ccdad
Add spdlog back as a requirement for now (#1780)
vyasr Jan 8, 2025
fb5e6bc
Make the stream module a part of the public API (#1775)
Matt711 Jan 16, 2025
d750a6e
Use GCC 13 in CUDA 12 conda builds. (#1773)
bdice Jan 17, 2025
67fd94d
Add upper bound to prevent usage of numba 0.61.0 (#1789)
galipremsagar Jan 22, 2025
c0bdd33
DOC v25.04 Updates [skip ci]
raydouglass Jan 23, 2025
dcd37ac
Add shellcheck to pre-commit and fix warnings (#1788)
gforsyth Jan 24, 2025
3caeb8a
Merge pull request #1793 from rapidsai/branch-25.02
GPUtester Jan 24, 2025
401483c
Build and test with CUDA 12.8.0 (#1797)
bdice Jan 28, 2025
3bc0178
Merge branch 'branch-25.02' into branch-25.04-merge-branch-25.02
vyasr Jan 29, 2025
b6f6dd0
Merge pull request #1799 from vyasr/branch-25.04-merge-branch-25.02
AyodeAwe Jan 29, 2025
b5bc0a0
Disable exec checks for `device_uvector::operator=` (#1790)
miscco Jan 30, 2025
2550156
Revert CUDA 12.8 shared workflow branch changes (#1805)
vyasr Jan 31, 2025
05e810a
disallow fallback to Make in wheel builds (#1804)
jameslamb Jan 31, 2025
1afdf44
Merge branch 'branch-25.02' into branch-25.04-merge-25.02
bdice Jan 31, 2025
f23ae31
Merge branch-25.02 into branch-25.04
bdice Jan 31, 2025
58fc846
Merge pull request #1806 from bdice/branch-25.04-merge-25.02
AyodeAwe Jan 31, 2025
45a4446
Migrate to NVKS for amd64 CI runners (#1803)
bdice Feb 1, 2025
fe66a24
Add `build_type` to workflow inputs (#1811)
gforsyth Feb 3, 2025
5dbb28b
Use build_type input (#1812)
bdice Feb 4, 2025
51283b0
Use nightly matrix for branch tests. (#1813)
bdice Feb 4, 2025
1eb9895
Use `rapids-pip-retry` in CI jobs that might need retries (#1814)
gforsyth Feb 5, 2025
3953d1c
Use shared-workflows branch-25.04 (#1816)
bdice Feb 7, 2025
f0a784a
Use new rapids-logger library (#1808)
vyasr Feb 10, 2025
ac8a99b
Remove unnecessary index (#1820)
vyasr Feb 10, 2025
670dcbb
mr/host: fix incorrect docs usage of device_memory_resource (#1809)
Feb 11, 2025
6e8539e
Apply IWYU changes and fix deprecated GTest usage (#1821)
bdice Feb 11, 2025
9f2e634
Create Conda CI test env in one step (#1824)
KyleFromNVIDIA Feb 12, 2025
17ba5ed
Update Changelog [skip ci]
AyodeAwe Feb 13, 2025
b2999d5
Merge pull request #1825 from rapidsai/branch-25.02
GPUtester Feb 13, 2025
cc969b6
Port to rattler-build (#1796)
gforsyth Feb 13, 2025
0d6083b
Consolidate more Conda solves in CI (#1828)
KyleFromNVIDIA Feb 14, 2025
1032c10
Require CMake 3.30.4 (#1826)
robertmaynard Feb 21, 2025
aa5d0b2
Update rattler-build recipe with assorted small fixes (#1832)
gforsyth Feb 21, 2025
3f674e3
Depend on rapids-logger in host to prevent redistribution (#1834)
bdice Feb 24, 2025
aa89bab
Sccache stats telemetry (#1830)
msarahan Feb 24, 2025
88eaaaf
Fixes for rattler recipe (#1835)
bdice Feb 24, 2025
e9f7f21
Use static gbench (#1837)
bdice Feb 25, 2025
0e34885
fix(rattler): resolve all overlinking errors (#1836)
gforsyth Feb 25, 2025
a757740
Add telemetry setup to build workflows (#1838)
bdice Feb 26, 2025
f26cc7e
use gha-tools rapids-telemetry-setup for mkdir -p (#1839)
msarahan Feb 26, 2025
d1a5f1b
Add OOM fail reason, attempted allocation size to exception messages …
pmattione-nvidia Feb 26, 2025
81ea864
fix(rattler): force `cuda_major` and `date_string` to be strings (#1842)
gforsyth Feb 26, 2025
01edf5a
Revert "Add OOM fail reason, attempted allocation size to exception m…
pmattione-nvidia Feb 26, 2025
844464b
fix GITHUB_WORKSPACE not being present locally (#1841)
msarahan Feb 28, 2025
b44ebb6
Add basic example. (#1800)
bdice Mar 1, 2025
dea0b21
Retry error logging (#1844)
pmattione-nvidia Mar 4, 2025
4a1727e
Fix for -fdebug-prefix-map breaking sccache (#1846)
bdice Mar 4, 2025
866a40e
Add tests for RMM internal macros. (#1847)
bdice Mar 5, 2025
d8b7dac
Run examples in CI (#1850)
bdice Mar 6, 2025
9432761
Fix dependencies.yaml for update-version.sh (#1859)
raydouglass Mar 13, 2025
015b3e9
DOC v25.06 Updates [skip ci]
raydouglass Mar 13, 2025
f87d7a6
Embed `__FILE__` as C-string for prefix replacement (#1858)
jakirkham Mar 13, 2025
97ec12d
Merge pull request #1860 from rapidsai/branch-25.04
GPUtester Mar 13, 2025
019228d
Fix run export on cudatoolkit (#1862)
vyasr Mar 17, 2025
06bbc05
Merge pull request #1863 from rapidsai/branch-25.04
GPUtester Mar 17, 2025
c66ded5
Add async view memory resource bindings to Python. (#1864)
bdice Mar 18, 2025
f070ea9
Merge pull request #1869 from rapidsai/branch-25.04
GPUtester Mar 18, 2025
71db9be
Error if LIBCUDACXX_ENABLE_EXPERIMENTAL_MEMORY_RESOURCE is not define…
bdice Mar 18, 2025
68c326e
Merge pull request #1870 from rapidsai/branch-25.04
GPUtester Mar 18, 2025
7f0cead
Set mempool hw_decompress flag if driver supports it (#1854)
wence- Mar 18, 2025
982d0e8
Merge pull request #1871 from rapidsai/branch-25.04
GPUtester Mar 18, 2025
c6773f2
Revert "Set mempool hw_decompress flag if driver supports it (#1854)"…
wence- Mar 19, 2025
7428e2d
Merge pull request #1874 from rapidsai/branch-25.04
GPUtester Mar 19, 2025
ef8eca4
refactor(rattler): enable strict channel priority for builds (#1867)
gforsyth Mar 21, 2025
0835c54
Fixed documentation example for `DeviceBuffer.to_device` (#1881)
TomAugspurger Mar 31, 2025
7529f92
Streamlining wheel builds to use fixed location and uploading build a…
jayavenkatesh19 Mar 31, 2025
ee938a3
Fix logger macros (#1884)
vyasr Apr 7, 2025
da3f558
[pre-commit.ci] pre-commit autoupdate (#1885)
pre-commit-ci[bot] Apr 8, 2025
6c23695
Update Changelog [skip ci]
AyodeAwe Apr 9, 2025
069bc69
Merge pull request #1888 from rapidsai/branch-25.04
GPUtester Apr 9, 2025
412d6a0
Set mempool hw_decompress flag if driver supports it (#1875)
bdice Apr 9, 2025
82c3288
Add ARM conda environments (#1889)
bdice Apr 10, 2025
9a9bc1d
Vendor RAPIDS.cmake to avoid network call. (#1886)
bdice Apr 10, 2025
8bae350
Auto-sync draft PRs (#1890)
bdice Apr 11, 2025
a828642
Move RMM C++ code into cpp directory. (#1883)
bdice Apr 15, 2025
c7a3314
remove mkdir and test corresponding shared workflow (#1892)
msarahan Apr 16, 2025
ace3fdb
Revert "Auto-sync draft PRs" (#1891)
bdice Apr 21, 2025
ab23e71
Download build artifacts from Github for CI (#1895)
jayavenkatesh19 Apr 22, 2025
1704990
Publish wheels and conda packages from Github Artifacts (#1897)
jayavenkatesh19 Apr 24, 2025
605feb4
Revert "Publish wheels and conda packages from Github Artifacts" (#1898)
bdice Apr 25, 2025
7506cf7
DOC v25.08 Updates [skip ci]
raydouglass Apr 30, 2025
0c9fe21
Add support for Python 3.13 (#1851)
bdice May 2, 2025
5149275
Merge branch 'branch-25.06' into branch-25.08
gforsyth May 2, 2025
c55ef4e
Merge pull request #1905 from gforsyth/branch-25.08-merge-25.06
AyodeAwe May 2, 2025
a66a7ea
Fix cpp wheel name to librmm. (#1903)
bdice May 7, 2025
efba884
Merge pull request #1906 from rapidsai/branch-25.06
GPUtester May 7, 2025
dbd8cc7
Build and test with CUDA 12.9.0 (#1907)
bdice May 8, 2025
8e19009
Convert part of RMM to a precompiled library (#1896)
bdice May 11, 2025
a087b7c
Use auditwheel to properly retag the wheel (#1913)
vyasr May 12, 2025
36cd902
Update Readme for the logging `set_level` (#1911)
JigaoLuo May 12, 2025
603107a
Merge branch 'branch-25.06' into branch-25.08-merge-branch-25.06
vyasr May 12, 2025
cf408fd
Merge pull request #1914 from vyasr/branch-25.08-merge-branch-25.06
raydouglass May 12, 2025
b30828d
Quote head_rev in conda recipes (#1915)
bdice May 13, 2025
0697e9e
Merge pull request #1916 from rapidsai/branch-25.06
GPUtester May 13, 2025
e9f7d35
Update to clang 20 (#1918)
bdice May 14, 2025
b951a11
Merge pull request #1919 from rapidsai/branch-25.06
GPUtester May 14, 2025
ecc6ca7
Move docs to top level. (#1917)
bdice May 14, 2025
dc5004d
Merge pull request #1920 from rapidsai/branch-25.06
GPUtester May 14, 2025
1226490
Finish CUDA 12.9 migration and use branch-25.06 workflows (#1921)
bdice May 15, 2025
ad4754d
Expose option to enable fabric memory handle support to Python (#1787)
pentschev May 17, 2025
c8eddbc
Merge branch 'branch-25.06' into branch-25.08-merge-25.06
gforsyth May 19, 2025
1e0dc73
Merge pull request #1925 from gforsyth/branch-25.08-merge-25.06
AyodeAwe May 19, 2025
7d9e347
use 'rapids-init-pip' in wheel CI, other CI changes (#1926)
jameslamb May 21, 2025
5243fb4
Merge pull request #1927 from rapidsai/branch-25.06
GPUtester May 21, 2025
462d2ba
stop uploading packages to downloads.rapids.ai (#1929)
jameslamb May 27, 2025
e7356ab
Remove CUDA 11 devcontainers and update CI scripts (#1933)
bdice May 30, 2025
d7b9538
Merge pull request #1942 from gforsyth/hotfix_pytest
gforsyth Jun 4, 2025
5d83d4c
Merge pull request #1943 from rapidsai/branch-25.06
GPUtester Jun 4, 2025
013e203
Run system MR tests in isolation. (#1945)
bdice Jun 4, 2025
ccd5c75
Merge pull request #1946 from rapidsai/branch-25.06
GPUtester Jun 4, 2025
2e44892
Update Changelog [skip ci]
raydouglass Jun 5, 2025
e5b1c01
Merge pull request #1947 from rapidsai/branch-25.06
GPUtester Jun 5, 2025
ef5d84c
Temporarily disable failing test on HMM systems. (#1950)
bdice Jun 10, 2025
27b3dc2
refactor(rattler): remove cuda11 options and general cleanup (#1932)
gforsyth Jun 10, 2025
07dec92
Remove CUDA 11 from dependencies.yaml (#1934)
KyleFromNVIDIA Jun 10, 2025
c4f8960
Fix race conditions and deadlocks in REPLAY_BENCH (#1940)
wence- Jun 10, 2025
f9ff11a
Fix Python path in CONTRIBUTING.md (#1936)
bdice Jun 10, 2025
a0dd1b9
Add managed memory resource to replay benchmark (#1938)
pentschev Jun 10, 2025
db325e6
Update branches that trigger nightlies (#1954)
raydouglass Jun 11, 2025
a4e28c1
Adding GH_TOKEN pass-through to summarize job (#1956)
msarahan Jun 12, 2025
0016ffb
Implemented device_uvector's reverse iterators (#1937)
lamarrr Jun 17, 2025
8f10dc7
Update cxxopts to 3.3.1. (#1962)
bdice Jun 17, 2025
ddaf047
Make RMM easier to BUILD with LLVM: (#1951)
vitor1001 Jun 18, 2025
f24903a
fix use-after-free in `tracking_resource_adaptor` (#1966)
legrosbuffle Jun 18, 2025
3c00f19
Fix nullptr dereference in `mr_ref_test`. (#1968)
legrosbuffle Jun 18, 2025
17c7545
Revert Sphinx pinning (#1970)
bdice Jun 25, 2025
6bd6560
refactor(shellcheck): enable for entire repo and fix all warnings (#1…
gforsyth Jun 25, 2025
d07133f
test changes to rapids-github-run-id (#1972)
jameslamb Jun 27, 2025
31f445e
Revert "test changes to rapids-github-run-id (#1972)" (#1974)
jameslamb Jun 27, 2025
ec8960f
Use CUDA 12.9 in Conda, Devcontainers, Spark, GHA, etc. (#1973)
jakirkham Jun 30, 2025
b4c3a1b
add docs on CI workflow inputs (#1975)
jameslamb Jul 1, 2025
95dda8e
Move more implementations to precompiled shared library (#1980)
bdice Jul 11, 2025
a67d70f
[pre-commit.ci] pre-commit autoupdate (#1979)
pre-commit-ci[bot] Jul 11, 2025
7e29204
Update Python build instructions to include librmm wheel (#1978)
gmarkall Jul 11, 2025
a68fdfe
Update requirements to CUDA 12.0+ (#1984)
bdice Jul 11, 2025
296a492
fix(docker): use versioned `-latest` tag for all `rapidsai` images (#…
gforsyth Jul 17, 2025
078c924
DOC v25.10 Updates [skip ci]
AyodeAwe Jul 17, 2025
c5874b3
chore: remove unused line from update-version.sh (#1989)
gforsyth Jul 17, 2025
c40c95f
Merge pull request #1990 from rapidsai/branch-25.08
GPUtester Jul 17, 2025
fd5bb01
Revert "Update branches that trigger nightlies (#1954)" (#1988)
gforsyth Jul 17, 2025
ed44697
Merge pull request #1991 from rapidsai/branch-25.08
GPUtester Jul 17, 2025
9d6c0f1
Use size_type in device_uvector (#1992)
bdice Jul 21, 2025
e447cd5
Merge pull request #1993 from rapidsai/branch-25.08
GPUtester Jul 21, 2025
c99163d
Allow latest OS in devcontainers (#1997)
bdice Jul 24, 2025
3bab478
Use GCC 14 in conda builds. (#1963)
vyasr Jul 25, 2025
1d304e2
Update build infra to support new branching strategy (#1994)
robertmaynard Jul 25, 2025
6e5b65e
Use std::for_each instead of std::equal in test (#1999)
vyasr Jul 25, 2025
e1d777a
Move more implementations to precompiled shared library (part 2) (#1983)
bdice Jul 28, 2025
8600dbe
[StepSecurity] Apply security best practices (#2000)
stepsecurity-app[bot] Jul 30, 2025
fd2b7c5
Fix aligned resource adaptor bug when alignment is less than 256. (#2…
bdice Aug 2, 2025
b6bb091
Update to use CUDA runtime APIs that work in CUDA 12 and 13 (#2004)
robertmaynard Aug 4, 2025
72b1563
ci(labeler): update labeler action to @v5 (#2006)
gforsyth Aug 4, 2025
daf60f2
Update rapids-build-backend to 0.4.1 (#2007)
KyleFromNVIDIA Aug 5, 2025
29dd323
Update Changelog [skip ci]
AyodeAwe Aug 6, 2025
9f7a447
Merge pull request #2009 from rapidsai/branch-25.08
GPUtester Aug 6, 2025
48492f1
Skip test on HMM systems with older CUDA drivers (#1944)
bdice Aug 8, 2025
1d3a01c
Add numba-cuda to fix errors on driver 580+. (#2013)
bdice Aug 9, 2025
8474569
Update rapids_config to handle user defined branch name (#2010)
robertmaynard Aug 9, 2025
b80ebf7
Update to numba-cuda >=0.18.0,<0.19.0a0 (#2019)
bdice Aug 12, 2025
1f69b36
Change pylibrmm Stream.view() method to noexcept (#2020)
davidwendt Aug 18, 2025
d5f1641
Add CUDA 13.0.0 devcontainers (#2012)
bdice Aug 18, 2025
3e00b2f
Minor improvements to README (#2018)
bdice Aug 18, 2025
2589030
Build and test with CUDA 13.0.0 (#2021)
jameslamb Aug 18, 2025
b6014ee
Use build cluster in devcontainers (#2016)
trxcllnt Aug 19, 2025
6fc6831
Update dependencies to align with other repos adopting CUDA 13 (#2022)
bdice Aug 20, 2025
81d566d
Refactor device capability checks, fix prefetching bug on WSL (#2014)
bdice Aug 22, 2025
93a84d4
Require numba-cuda>=0.19.1 to get fixes for numba==0.60 support (#2024)
bdice Aug 22, 2025
7cef2f5
Update rapids-dependency-file-generator (#2027)
KyleFromNVIDIA Aug 26, 2025
e023f81
Use branch-25.10 again (#2030)
jameslamb Sep 5, 2025
50d25c4
Always release the GIL before any operation that could acquire locks …
vyasr Sep 8, 2025
b0a2a8a
update dependencies: cuda-python (>=12.9.2 / >=13.0.1) (#2031)
jameslamb Sep 9, 2025
163c84a
Skip callback memory tests on integrated memory systems, add docs (#2…
bdice Sep 10, 2025
de85ed3
Support building with CCCL 3.1.0 (#2017)
bdice Sep 16, 2025
4cd5dbf
Configure repo for automatic release notes generation (#2037)
AyodeAwe Sep 22, 2025
278d559
Add option to create non-blocking streams (#2036)
wence- Sep 23, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
22 changes: 13 additions & 9 deletions .clang-format
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ AlignTrailingComments: true
AllowAllArgumentsOnNextLine: true
AllowAllConstructorInitializersOnNextLine: true
AllowAllParametersOfDeclarationOnNextLine: true
AllowShortBlocksOnASingleLine: true
AllowShortBlocksOnASingleLine: true
AllowShortCaseLabelsOnASingleLine: true
AllowShortEnumsOnASingleLine: true
AllowShortFunctionsOnASingleLine: All
Expand All @@ -27,7 +27,7 @@ AlwaysBreakAfterDefinitionReturnType: None
AlwaysBreakAfterReturnType: None
AlwaysBreakBeforeMultilineStrings: true
AlwaysBreakTemplateDeclarations: Yes
BinPackArguments: false
BinPackArguments: false
BinPackParameters: false
BraceWrapping:
AfterClass: false
Expand All @@ -46,6 +46,7 @@ BraceWrapping:
SplitEmptyFunction: false
SplitEmptyRecord: false
SplitEmptyNamespace: false
BreakAfterAttributes: Leave
BreakAfterJavaFieldAnnotations: false
BreakBeforeBinaryOperators: None
BreakBeforeBraces: WebKit
Expand All @@ -71,17 +72,20 @@ ForEachMacros:
- foreach
- Q_FOREACH
- BOOST_FOREACH
IncludeBlocks: Preserve
IncludeBlocks: Regroup
IncludeCategories:
- Regex: '^<ext/.*\.h>'
Priority: 2
- Regex: '^<.*\.h>'
- Regex: '^"' # quoted includes
Priority: 1
- Regex: '^<.*'
- Regex: '^<rmm/' # RMM includes
Priority: 2
- Regex: '.*'
- Regex: '^<(thrust|cub|cuda)/' # CCCL includes
Priority: 3
- Regex: '^<(cooperative_groups|cuco|cuda.h|cuda_runtime|device_types|math_constants|nvtx3)' # CUDA includes
Priority: 3
IncludeIsMainRegex: '([-_](test|unittest))?$'
- Regex: '^<.*\..*' # other system includes (e.g. with a '.')
Priority: 4
- Regex: '^<[^.]+' # STL includes (no '.')
Priority: 5
IndentCaseLabels: true
IndentPPDirectives: None
IndentWidth: 2
Expand Down
60 changes: 60 additions & 0 deletions .devcontainer/Dockerfile
Original file line number Diff line number Diff line change
@@ -0,0 +1,60 @@
# syntax=docker/dockerfile:1.5

ARG BASE
ARG PYTHON_PACKAGE_MANAGER=conda

FROM ${BASE} as pip-base

ENV DEFAULT_VIRTUAL_ENV=rapids

FROM ${BASE} as conda-base

ENV DEFAULT_CONDA_ENV=rapids

FROM ${PYTHON_PACKAGE_MANAGER}-base

ARG TARGETARCH

ARG CUDA
ENV CUDAARCHS="RAPIDS"
ENV CUDA_VERSION="${CUDA_VERSION:-${CUDA}}"

ARG PYTHON_PACKAGE_MANAGER
ENV PYTHON_PACKAGE_MANAGER="${PYTHON_PACKAGE_MANAGER}"

ENV PYTHONSAFEPATH="1"
ENV PYTHONUNBUFFERED="1"
ENV PYTHONDONTWRITEBYTECODE="1"

ENV HISTFILE="/home/coder/.cache/._bash_history"

###
# sccache configuration
###
ENV AWS_ROLE_ARN="arn:aws:iam::279114543810:role/nv-gha-token-sccache-devs"
ENV SCCACHE_REGION="us-east-2"
ENV SCCACHE_BUCKET="rapids-sccache-devs"
# 2hr (1 minute longer than sccache-dist request timeout)
ENV SCCACHE_IDLE_TIMEOUT=7200

###
# sccache-dist configuration
###
# Enable sccache-dist by default
ENV DEVCONTAINER_UTILS_ENABLE_SCCACHE_DIST=1
# Compile locally if max retries exceeded
ENV SCCACHE_DIST_FALLBACK_TO_LOCAL_COMPILE=true
# Retry transient errors 4 times (for a total of 5 attempts)
ENV SCCACHE_DIST_MAX_RETRIES=4
ENV SCCACHE_DIST_CONNECT_TIMEOUT=30
ENV SCCACHE_DIST_CONNECTION_POOL=false
# 1hr 59min (to accommodate debug builds)
ENV SCCACHE_DIST_REQUEST_TIMEOUT=7140
ENV SCCACHE_DIST_KEEPALIVE_ENABLED=true
ENV SCCACHE_DIST_KEEPALIVE_INTERVAL=20
ENV SCCACHE_DIST_KEEPALIVE_TIMEOUT=600
ENV SCCACHE_DIST_URL="https://${TARGETARCH}.linux.sccache.rapids.nvidia.com"

# Build as much in parallel as possible
ENV INFER_NUM_DEVICE_ARCHITECTURES=1
ENV MAX_DEVICE_OBJ_TO_COMPILE_IN_PARALLEL=20
35 changes: 35 additions & 0 deletions .devcontainer/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
# RMM Development Containers

This directory contains [devcontainer configurations](https://containers.dev/implementors/json_reference/) for using VSCode to [develop in a container](https://code.visualstudio.com/docs/devcontainers/containers) via the `Remote Containers` [extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers) or [GitHub Codespaces](https://github.com/codespaces).

This container is a turnkey development environment for building and testing the RMM C++ and Python libraries.

## Table of Contents

* [Prerequisites](#prerequisites)
* [Host bind mounts](#host-bind-mounts)
* [Launch a Dev Container](#launch-a-dev-container)

## Prerequisites

* [VSCode](https://code.visualstudio.com/download)
* [VSCode Remote Containers extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers)

## Host bind mounts

By default, the following directories are bind-mounted into the devcontainer:

* `${repo}:/home/coder/rmm`
* `${repo}/../.aws:/home/coder/.aws`
* `${repo}/../.local:/home/coder/.local`
* `${repo}/../.cache:/home/coder/.cache`
* `${repo}/../.conda:/home/coder/.conda`
* `${repo}/../.config:/home/coder/.config`

This ensures caches, configurations, dependencies, and your commits are persisted on the host across container runs.

## Launch a Dev Container

To launch a devcontainer from VSCode, open the RMM repo and select the "Reopen in Container" button in the bottom right:<br/><img src="https://user-images.githubusercontent.com/178183/221771999-97ab29d5-e718-4e5f-b32f-2cdd51bba25c.png"/>

Alternatively, open the VSCode command palette (typically `cmd/ctrl + shift + P`) and run the "Rebuild and Reopen in Container" command.
44 changes: 44 additions & 0 deletions .devcontainer/cuda12.9-conda/devcontainer.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,44 @@
{
"build": {
"context": "${localWorkspaceFolder}/.devcontainer",
"dockerfile": "${localWorkspaceFolder}/.devcontainer/Dockerfile",
"args": {
"CUDA": "12.9",
"PYTHON_PACKAGE_MANAGER": "conda",
"BASE": "rapidsai/devcontainers:25.10-cpp-mambaforge"
}
},
"runArgs": [
"--rm",
"--name",
"${localEnv:USER:anon}-rapids-${localWorkspaceFolderBasename}-25.10-cuda12.9-conda",
"--ulimit",
"nofile=500000"
],
"hostRequirements": {"gpu": "optional"},
"features": {
"ghcr.io/rapidsai/devcontainers/features/rapids-build-utils:25.10": {}
},
"overrideFeatureInstallOrder": [
"ghcr.io/rapidsai/devcontainers/features/rapids-build-utils"
],
"initializeCommand": ["/bin/bash", "-c", "mkdir -m 0755 -p ${localWorkspaceFolder}/../.{aws,cache,config,conda/pkgs,conda/${localWorkspaceFolderBasename}-cuda12.9-envs}"],
"postAttachCommand": ["/bin/bash", "-c", "if [ ${CODESPACES:-false} = 'true' ]; then . devcontainer-utils-post-attach-command; . rapids-post-attach-command; fi"],
"workspaceFolder": "/home/coder",
"workspaceMount": "source=${localWorkspaceFolder},target=/home/coder/rmm,type=bind,consistency=consistent",
"mounts": [
"source=${localWorkspaceFolder}/../.aws,target=/home/coder/.aws,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.cache,target=/home/coder/.cache,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.config,target=/home/coder/.config,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.conda/pkgs,target=/home/coder/.conda/pkgs,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.conda/${localWorkspaceFolderBasename}-cuda12.9-envs,target=/home/coder/.conda/envs,type=bind,consistency=consistent"
],
"customizations": {
"vscode": {
"extensions": [
"ms-python.flake8",
"nvidia.nsight-vscode-edition"
]
}
}
}
43 changes: 43 additions & 0 deletions .devcontainer/cuda12.9-pip/devcontainer.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,43 @@
{
"build": {
"context": "${localWorkspaceFolder}/.devcontainer",
"dockerfile": "${localWorkspaceFolder}/.devcontainer/Dockerfile",
"args": {
"CUDA": "12.9",
"PYTHON_PACKAGE_MANAGER": "pip",
"BASE": "rapidsai/devcontainers:25.10-cpp-cuda12.9"
}
},
"runArgs": [
"--rm",
"--name",
"${localEnv:USER:anon}-rapids-${localWorkspaceFolderBasename}-25.10-cuda12.9-pip",
"--ulimit",
"nofile=500000"
],
"hostRequirements": {"gpu": "optional"},
"features": {
"ghcr.io/rapidsai/devcontainers/features/rapids-build-utils:25.10": {}
},
"overrideFeatureInstallOrder": [
"ghcr.io/rapidsai/devcontainers/features/rapids-build-utils"
],
"initializeCommand": ["/bin/bash", "-c", "mkdir -m 0755 -p ${localWorkspaceFolder}/../.{aws,cache,config/pip,local/share/${localWorkspaceFolderBasename}-cuda12.9-venvs}"],
"postAttachCommand": ["/bin/bash", "-c", "if [ ${CODESPACES:-false} = 'true' ]; then . devcontainer-utils-post-attach-command; . rapids-post-attach-command; fi"],
"workspaceFolder": "/home/coder",
"workspaceMount": "source=${localWorkspaceFolder},target=/home/coder/rmm,type=bind,consistency=consistent",
"mounts": [
"source=${localWorkspaceFolder}/../.aws,target=/home/coder/.aws,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.cache,target=/home/coder/.cache,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.config,target=/home/coder/.config,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.local/share/${localWorkspaceFolderBasename}-cuda12.9-venvs,target=/home/coder/.local/share/venvs,type=bind,consistency=consistent"
],
"customizations": {
"vscode": {
"extensions": [
"ms-python.flake8",
"nvidia.nsight-vscode-edition"
]
}
}
}
42 changes: 42 additions & 0 deletions .devcontainer/cuda13.0-conda/devcontainer.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,42 @@
{
"build": {
"context": "${localWorkspaceFolder}/.devcontainer",
"dockerfile": "${localWorkspaceFolder}/.devcontainer/Dockerfile",
"args": {
"CUDA": "13.0",
"PYTHON_PACKAGE_MANAGER": "conda",
"BASE": "rapidsai/devcontainers:25.10-cpp-mambaforge"
}
},
"runArgs": [
"--rm",
"--name",
"${localEnv:USER:anon}-rapids-${localWorkspaceFolderBasename}-25.10-cuda13.0-conda"
],
"hostRequirements": {"gpu": "optional"},
"features": {
"ghcr.io/rapidsai/devcontainers/features/rapids-build-utils:25.10": {}
},
"overrideFeatureInstallOrder": [
"ghcr.io/rapidsai/devcontainers/features/rapids-build-utils"
],
"initializeCommand": ["/bin/bash", "-c", "mkdir -m 0755 -p ${localWorkspaceFolder}/../.{aws,cache,config,conda/pkgs,conda/${localWorkspaceFolderBasename}-cuda13.0-envs}"],
"postAttachCommand": ["/bin/bash", "-c", "if [ ${CODESPACES:-false} = 'true' ]; then . devcontainer-utils-post-attach-command; . rapids-post-attach-command; fi"],
"workspaceFolder": "/home/coder",
"workspaceMount": "source=${localWorkspaceFolder},target=/home/coder/rmm,type=bind,consistency=consistent",
"mounts": [
"source=${localWorkspaceFolder}/../.aws,target=/home/coder/.aws,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.cache,target=/home/coder/.cache,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.config,target=/home/coder/.config,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.conda/pkgs,target=/home/coder/.conda/pkgs,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.conda/${localWorkspaceFolderBasename}-cuda13.0-envs,target=/home/coder/.conda/envs,type=bind,consistency=consistent"
],
"customizations": {
"vscode": {
"extensions": [
"ms-python.flake8",
"nvidia.nsight-vscode-edition"
]
}
}
}
41 changes: 41 additions & 0 deletions .devcontainer/cuda13.0-pip/devcontainer.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@
{
"build": {
"context": "${localWorkspaceFolder}/.devcontainer",
"dockerfile": "${localWorkspaceFolder}/.devcontainer/Dockerfile",
"args": {
"CUDA": "13.0",
"PYTHON_PACKAGE_MANAGER": "pip",
"BASE": "rapidsai/devcontainers:25.10-cpp-cuda13.0"
}
},
"runArgs": [
"--rm",
"--name",
"${localEnv:USER:anon}-rapids-${localWorkspaceFolderBasename}-25.10-cuda13.0-pip"
],
"hostRequirements": {"gpu": "optional"},
"features": {
"ghcr.io/rapidsai/devcontainers/features/rapids-build-utils:25.10": {}
},
"overrideFeatureInstallOrder": [
"ghcr.io/rapidsai/devcontainers/features/rapids-build-utils"
],
"initializeCommand": ["/bin/bash", "-c", "mkdir -m 0755 -p ${localWorkspaceFolder}/../.{aws,cache,config/pip,local/share/${localWorkspaceFolderBasename}-cuda13.0-venvs}"],
"postAttachCommand": ["/bin/bash", "-c", "if [ ${CODESPACES:-false} = 'true' ]; then . devcontainer-utils-post-attach-command; . rapids-post-attach-command; fi"],
"workspaceFolder": "/home/coder",
"workspaceMount": "source=${localWorkspaceFolder},target=/home/coder/rmm,type=bind,consistency=consistent",
"mounts": [
"source=${localWorkspaceFolder}/../.aws,target=/home/coder/.aws,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.cache,target=/home/coder/.cache,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.config,target=/home/coder/.config,type=bind,consistency=consistent",
"source=${localWorkspaceFolder}/../.local/share/${localWorkspaceFolderBasename}-cuda13.0-venvs,target=/home/coder/.local/share/venvs,type=bind,consistency=consistent"
],
"customizations": {
"vscode": {
"extensions": [
"ms-python.flake8",
"nvidia.nsight-vscode-edition"
]
}
}
}
18 changes: 12 additions & 6 deletions .github/CODEOWNERS
Original file line number Diff line number Diff line change
Expand Up @@ -10,9 +10,15 @@ python/ @rapidsai/rmm-python-codeowners
**/CMakeLists.txt @rapidsai/rmm-cmake-codeowners
**/cmake/ @rapidsai/rmm-cmake-codeowners

#build/ops code owners
.github/ @rapidsai/ops-codeowners
ci/ @rapidsai/ops-codeowners
conda/ @rapidsai/ops-codeowners
**/Dockerfile @rapidsai/ops-codeowners
**/.dockerignore @rapidsai/ops-codeowners
#CI code owners
/.github/ @rapidsai/ci-codeowners
/ci/ @rapidsai/ci-codeowners
/.pre-commit-config.yaml @rapidsai/ci-codeowners
/.shellcheckrc @rapidsai/ci-codeowners

#packaging code owners
/.devcontainer/ @rapidsai/packaging-codeowners
/conda/ @rapidsai/packaging-codeowners
/dependencies.yaml @rapidsai/packaging-codeowners
/build.sh @rapidsai/packaging-codeowners
pyproject.toml @rapidsai/packaging-codeowners
1 change: 0 additions & 1 deletion .github/ISSUE_TEMPLATE/documentation-request.md
Original file line number Diff line number Diff line change
Expand Up @@ -30,4 +30,3 @@ A clear and concise description of what documentation is needed and why.

**Steps taken to search for needed documentation**
List any steps you have taken.

Loading
Loading