v1.9.5

Bug Fixes

• Fix configuration file reading order

Full Changelog: v1.9.4...v1.9.5

v1.9.4

Bug Fixes

• Fix error of HBOX_CLIENT_OPTS undefined

Full Changelog: v1.9.3...v1.9.4

v1.9.3

Bug Fixes and Other Changes

• Fix cli parsing for --conf, --intput and --output
• Avoid RunJar to unjar the client into a temp dir
• Open HBOX_CLIENT_OPTS flags

Full Changelog: v1.9.2...v1.9.3

v1.9.2

Bug Fixes and Other Changes

• Fix missing mpi logs.
• Add role and rank in job history page.

Full Changelog: v1.9.1...v1.9.2

v1.9.1

Bug Fixes and Other Changes

• support switch submitting user in azkaban.

Full Changelog: v1.9.0...v1.9.1

v1.9.0

Major Features And Improvements

• support full mobile deployment of OpenMPI on AM.
• format Java code using palantir-java-format.
• support emitting opentelemetry traces.

Bug Fixes and Other Changes

• fix hbox-logs issue and improve MPI orted status monitoring.
• fix PATH and LD_LIBRARY_PATH for mpi jobs .
• fix hadoop ugi and shellcheck error.

Full Changelog: v1.8.1...v1.9.0

v1.8.0

What's Changed

• Support GPU training
• Support multiple version of yarn (>= 2.6)
• add faq by @yuyajian in #15
• fix the board history display by @jiarunying in #17
• reset worker num when less than inputfile number by @liyuance in #35
• xlearning container allocate port from 20000 to 30000 by default by @FANNG1 in #45
• add docker support by @SuperbDong in #64
• Tensorflow example hangs when using multiple workers by @lshmouse in #62

New Contributors

• @yuyajian made their first contribution in #15
• @jiarunying made their first contribution in #17
• @liyuance made their first contribution in #35
• @FANNG1 made their first contribution in #45
• @SuperbDong made their first contribution in #64
• @lshmouse made their first contribution in #62

Full Changelog: v1.7.2...v1.8.0

What's Changed

• Tensorflow example hangs when using multiple workers by @lshmouse in #62

New Contributors

• @lshmouse made their first contribution in #62

Full Changelog: v1.4...v1.8.0

v1.8.0-beta2

What's Changed

• add faq by @yuyajian in #15
• fix the board history display by @jiarunying in #17
• reset worker num when less than inputfile number by @liyuance in #35
• xlearning container allocate port from 20000 to 30000 by default by @FANNG1 in #45
• add docker support by @SuperbDong in #64
• Tensorflow example hangs when using multiple workers by @lshmouse in #62

New Contributors

• @yuyajian made their first contribution in #15
• @jiarunying made their first contribution in #17
• @liyuance made their first contribution in #35
• @FANNG1 made their first contribution in #45
• @SuperbDong made their first contribution in #64
• @lshmouse made their first contribution in #62

Full Changelog: https://github.com/Qihoo360/hbox/commits/v1.8.0-beta2

XLearning 1.4

Release XLearning 1.4

Major Features And Improvements

• Support the application running on the docker
• Support the mpi application
• ClusterDef is avaliable for TensorFlow Distribution Strategy API
• Allow the amount of memory to be set separately for chief and estimator worker for TensorFlow Application
• Specify the Yarn node label for job execution
• Multi-threads upload the output
• Allow the inter-result incremental upload
• Support the regular matching for input path

Bug Fixes and Other Changes

• The memory usage adjustment prompt is only displayed when the application finish status is successed.

XLearning 1.3

Release XLearning 1.3

Major Features And Improvements

• Support the lightLDA, see examples/lightLDA for use
• Support the xflow, see examples/xflow for use
• By submitting the configuration parameter to support the user-defined environment variable settings
• Setting the last worker as estimator role of the distribute TensorFlow application if the user set the tf-evaluator as true, see examples/tfEstimators for use
• Define the single worker index to save the output by set the output-index
• Port reservation mechanism optimization
• Local data container allocation priority mechanism
• Display resource application and usage information
• ps role function expansion: more convenient metrics use information rendering and output output upload

Bug Fixes and Other Changes

• Container waits for the remaining machine port addresses to be stuck in the process due to the failure of the Container in distributed mode
• After the worker applies, the number of redundant applications is released, and the remove request operation is added
• Application failed due to excessive environment variables too long of the input in PLACEHOLDER mode
• Job execution judgment failure condition control
• The status code returns incorrectly when the Container successfully exits