# Latest **URL:** https://community.konduit.ai/latest.md [Latest](https://community.konduit.ai/latest.md) · [Categories](https://community.konduit.ai/categories.md) --- ## [How would you implement weight sharing?](https://community.konduit.ai/t/how-would-you-implement-weight-sharing/3537)
**Author:** [@Lana](https://community.konduit.ai/u/Lana)\ **Replies:** 3\ **Last updated:** [August 26, 2026, 10:44am UTC](https://community.konduit.ai/t/how-would-you-implement-weight-sharing/3537 "2026-08-26T10:44:07Z")
I am implementing a famous model where you have in python with tf.GradientTape() as g: for i in tf.range(60): x = model(x) loss = tf.reduce\_mean(loss\_f(x)) grads = g.gradient(loss, model.weights) Pytho… --- ## [Do several forward passes before one backward pass](https://community.konduit.ai/t/do-several-forward-passes-before-one-backward-pass/3534)
**Author:** [@Lana](https://community.konduit.ai/u/Lana)\ **Replies:** 4\ **Last updated:** [August 9, 2026, 11:28am UTC](https://community.konduit.ai/t/do-several-forward-passes-before-one-backward-pass/3534 "2026-08-09T11:28:33Z")
I am looking for a way to manually call a backwards pass on a model. This page implies that there is a sd.execBackwards() function in 1.0.0-M2.1, but it doesn’t seem to actually exist in the library (neither does sd.exe… --- ## [No more stack function?](https://community.konduit.ai/t/no-more-stack-function/3532)
**Author:** [@Lana](https://community.konduit.ai/u/Lana)\ **Replies:** 3\ **Last updated:** [July 30, 2026, 1:24pm UTC](https://community.konduit.ai/t/no-more-stack-function/3532 "2026-07-30T13:24:40Z")
The manual gives examples of Nd4j.stack() as INDArray batch = Nd4j.stack(0, sample1, sample2, sample3); But java does not find any stack function, only vstack and hstack. What am I missing? --- ## [New release soon](https://community.konduit.ai/t/new-release-soon/3530)
**Author:** [@agibsonccc](https://community.konduit.ai/u/agibsonccc)\ **Replies:** 7\ **Last updated:** [July 10, 2026, 10:18pm UTC](https://community.konduit.ai/t/new-release-soon/3530 "2026-07-10T22:18:01Z")
Hello all: After a long time waiting the release will be coming out. You can get a preview of what to expect here with the links below: Some upcoming things to expect: Dl4j as it stands will NOT be what it was. The … --- ## [KerasModelImport: simple example of saving a keras model?](https://community.konduit.ai/t/kerasmodelimport-simple-example-of-saving-a-keras-model/3521)
**Author:** [@Lana](https://community.konduit.ai/u/Lana)\ **Replies:** 3\ **Last updated:** [June 18, 2026, 12:57am UTC](https://community.konduit.ai/t/kerasmodelimport-simple-example-of-saving-a-keras-model/3521 "2026-06-18T00:57:17Z")
Hello, I am trying to import a sequential model trained from keras, following the example at deeplearning4j-examples/tensorflow-keras-import-examples/src/main/java/org/deeplearning4j/modelimportexamples/keras/quickstart… --- ## [Is LSTM working in DeepLearning4J?](https://community.konduit.ai/t/is-lstm-working-in-deeplearning4j/3435)
**Author:** [@MonNomIzNoGoud](https://community.konduit.ai/u/MonNomIzNoGoud)\ **Replies:** 5\ **Last updated:** [May 16, 2026, 3:31pm UTC](https://community.konduit.ai/t/is-lstm-working-in-deeplearning4j/3435 "2026-05-16T15:31:33Z")
Hello. I was looking for a java NN framework in order to more smooth than predict one time series values based on a dozen or so other time series. I’ve stumbled on SANNET which looked promising but unfortunately the GRU/… --- ## [Dl4j-spring-boot-starter?](https://community.konduit.ai/t/dl4j-spring-boot-starter/3434)
**Author:** [@darius1973](https://community.konduit.ai/u/darius1973)\ **Replies:** 0\ **Last updated:** [April 13, 2026, 5:13pm UTC](https://community.konduit.ai/t/dl4j-spring-boot-starter/3434 "2026-04-13T17:13:49Z")
Hi DL4J team First of all congrats for this project/initiative. As currently the entire java AI community seems to be hypnoitized by LLM’s gen AI stuff, it is comforting to see that there are still ppl interested in dev… --- ## [Significant Performance Drop in \`nn.fit()\` method After Upgrading to NVIDIA 3060 and CUDA 11.6](https://community.konduit.ai/t/significant-performance-drop-in-nn-fit-method-after-upgrading-to-nvidia-3060-and-cuda-11-6/2902)
**Author:** [@Nasyumaro](https://community.konduit.ai/u/Nasyumaro)\ **Replies:** 8\ **Last updated:** [April 1, 2026, 4:07am UTC](https://community.konduit.ai/t/significant-performance-drop-in-nn-fit-method-after-upgrading-to-nvidia-3060-and-cuda-11-6/2902 "2026-04-01T04:07:47Z")
I have been using 1660ti and cuda10.2 with DL4J 1.0.0beta7. We have now changed to 3060, cuda11.6, and DL4J 1.0.0M2.1. memo The CUDA version was increased because the GPU is not compatible with 10.2. The reason we r… --- ## [Why is mini batch size passed to the shape of placeholders?](https://community.konduit.ai/t/why-is-mini-batch-size-passed-to-the-shape-of-placeholders/3432)
**Author:** [@Cezar](https://community.konduit.ai/u/Cezar)\ **Replies:** 5\ **Last updated:** [March 20, 2026, 8:19am UTC](https://community.konduit.ai/t/why-is-mini-batch-size-passed-to-the-shape-of-placeholders/3432 "2026-03-20T08:19:32Z")
Maybe a dumb question, but I thought that the dataset object contain mini batches, and batching is handled by the training functiin --- ## [When will the new stable version be released?](https://community.konduit.ai/t/when-will-the-new-stable-version-be-released/3428)
**Author:** [@cqiaoYc](https://community.konduit.ai/u/cqiaoYc)\ **Replies:** 4\ **Last updated:** [March 20, 2026, 8:08am UTC](https://community.konduit.ai/t/when-will-the-new-stable-version-be-released/3428 "2026-03-20T08:08:43Z")
With deep learning progressing so quickly, it’s been ages since the last stable update. I can’t wait for the new stable release. --- ## [NullPointerException org.nd4j.autodiff.samediff.internal.Variable.getOutputOfOp()](https://community.konduit.ai/t/nullpointerexception-org-nd4j-autodiff-samediff-internal-variable-getoutputofop/3278)
**Author:** [@adonnini](https://community.konduit.ai/u/adonnini)\ **Replies:** 173\ **Last updated:** [March 7, 2026, 9:09pm UTC](https://community.konduit.ai/t/nullpointerexception-org-nd4j-autodiff-samediff-internal-variable-getoutputofop/3278 "2026-03-07T21:09:42Z")
Hi, I am finally back to working on my implementation of " Attention Is All You Need" model and made good progress (I think). However, now I have run into a problem I am stuck on. Below, you will find the error log. P… --- ## [Keras Import: java.lang.String cast to java.util.List](https://community.konduit.ai/t/keras-import-java-lang-string-cast-to-java-util-list/3412)
**Author:** [@kelauder](https://community.konduit.ai/u/kelauder)\ **Replies:** 4\ **Last updated:** [March 4, 2026, 11:53pm UTC](https://community.konduit.ai/t/keras-import-java-lang-string-cast-to-java-util-list/3412 "2026-03-04T23:53:01Z")
I’m trying to import a ConvNet that was created it Python. I tried both separated Json model with H5 weights and combined H5 model. The java code is: String modelPath = "Model.h5"; ComputationGraph model =… --- ## [Snapshots unavailable in maven snapshots repository](https://community.konduit.ai/t/snapshots-unavailable-in-maven-snapshots-repository/3409)
**Author:** [@nk2](https://community.konduit.ai/u/nk2)\ **Replies:** 4\ **Last updated:** [March 4, 2026, 11:52pm UTC](https://community.konduit.ai/t/snapshots-unavailable-in-maven-snapshots-repository/3409 "2026-03-04T23:52:06Z")
I am trying to add the dependency on a couple of libraries from ND4J project. Given prior discussions on this forum I see that the snapshots should be published under version 1.0.0-SNAPSHOT with a different group id than… --- ## [Build from source for CUDA 12.8 error](https://community.konduit.ai/t/build-from-source-for-cuda-12-8-error/3414)
**Author:** [@manvendra-singh-2709](https://community.konduit.ai/u/manvendra-singh-2709)\ **Replies:** 5\ **Last updated:** [March 3, 2026, 5:43am UTC](https://community.konduit.ai/t/build-from-source-for-cuda-12-8-error/3414 "2026-03-03T05:43:48Z")
I want to build DL4J from source for my cuda 12.8 but it gives this error: \[ERROR\] Failed to execute goal org.bytedeco:javacpp:1.5.11:build (javacpp-cppbuild-validate) on project libnd4j: Execution javacpp-cppbuild-vali… --- ## [When will be the end time to support 1080 ti?](https://community.konduit.ai/t/when-will-be-the-end-time-to-support-1080-ti/3411)
**Author:** [@Booker](https://community.konduit.ai/u/Booker)\ **Replies:** 3\ **Last updated:** [January 21, 2026, 1:02am UTC](https://community.konduit.ai/t/when-will-be-the-end-time-to-support-1080-ti/3411 "2026-01-21T01:02:38Z")
When will be the end time to support 1080 ti ? --- ## [Stand alone jar file determination issues](https://community.konduit.ai/t/stand-alone-jar-file-determination-issues/3407)
**Author:** [@kelauder](https://community.konduit.ai/u/kelauder)\ **Replies:** 2\ **Last updated:** [January 15, 2026, 3:46pm UTC](https://community.konduit.ai/t/stand-alone-jar-file-determination-issues/3407 "2026-01-15T15:46:03Z")
I am trying to create a stand alone app that will not have access to the Maven. I have a Maven project that is working on my windows system. I ran the Maven dependency to get the list of jar files needed. I then crea… --- ## [New PRs not sychronized to main](https://community.konduit.ai/t/new-prs-not-sychronized-to-main/3408)
**Author:** [@Booker](https://community.konduit.ai/u/Booker)\ **Replies:** 4\ **Last updated:** [January 7, 2026, 8:27pm UTC](https://community.konduit.ai/t/new-prs-not-sychronized-to-main/3408 "2026-01-07T20:27:29Z")
seems the new 41 PRs have finished, why not merge them to main? --- ## [Can nd4j-onnxruntime use GPU for ONNX model inference?](https://community.konduit.ai/t/can-nd4j-onnxruntime-use-gpu-for-onnx-model-inference/3405)
**Author:** [@LiuJia](https://community.konduit.ai/u/LiuJia)\ **Replies:** 1\ **Last updated:** [October 14, 2025, 9:43am UTC](https://community.konduit.ai/t/can-nd4j-onnxruntime-use-gpu-for-onnx-model-inference/3405 "2025-10-14T09:43:18Z")
Can nd4j-onnxruntime use GPU for ONNX model inference? deeplearning4j-cuda-11.2 1.0.0-M1.1 nd4j-cuda-11.2 1.0.0-M1 nd4j-onnxruntime 1.0.0-M1.1 When I use this version of nd4j-onnxruntime for inference, the outp… --- ## [Float16 use gives cuda 700 error](https://community.konduit.ai/t/float16-use-gives-cuda-700-error/3401)
**Author:** [@markiemark](https://community.konduit.ai/u/markiemark)\ **Replies:** 3\ **Last updated:** [October 6, 2025, 9:42am UTC](https://community.konduit.ai/t/float16-use-gives-cuda-700-error/3401 "2025-10-06T09:42:46Z")
I have implemented a PSFormer using SameDiff, and it seems to work using dtype FLOAT. Hoping to get some faster training I tried with FLOAT16 (HALF) but run into cuda 700 errors. I’ve narrowed it down to the initial weig… --- ## [Not try to release new version now?](https://community.konduit.ai/t/not-try-to-release-new-version-now/3400)
**Author:** [@Booker](https://community.konduit.ai/u/Booker)\ **Replies:** 1\ **Last updated:** [September 25, 2025, 8:27pm UTC](https://community.konduit.ai/t/not-try-to-release-new-version-now/3400 "2025-09-25T20:27:28Z")
Not try to release new version now? --- ## [Support for cuda 13.0 toolkit?](https://community.konduit.ai/t/support-for-cuda-13-0-toolkit/3398)
**Author:** [@markiemark](https://community.konduit.ai/u/markiemark)\ **Replies:** 2\ **Last updated:** [August 25, 2025, 3:56pm UTC](https://community.konduit.ai/t/support-for-cuda-13-0-toolkit/3398 "2025-08-25T15:56:50Z")
I’m trying to get DL4J working with my RTX 5070 card, which means I need support for the cuda 13.0 toolkit (compute capability 12.0). By now I’ve figured I’m not going to have this working using the current sources. Any … --- ## [16KB page size support for android 15](https://community.konduit.ai/t/16kb-page-size-support-for-android-15/3389)
**Author:** [@TinTran64](https://community.konduit.ai/u/TinTran64)\ **Replies:** 1\ **Last updated:** [August 25, 2025, 11:43am UTC](https://community.konduit.ai/t/16kb-page-size-support-for-android-15/3389 "2025-08-25T11:43:32Z")
Hi! Google required all Android apps to target Android 15 and support 16KB page size. The libjnind4jcpu.so and libnd4jcpu.so need to be recompiled using r28 NDK. How can I recompile these files from source? I want to co… --- ## [How to add a BatchNorm layer after a 1D CNN layer?](https://community.konduit.ai/t/how-to-add-a-batchnorm-layer-after-a-1d-cnn-layer/3381)
**Author:** [@cqiaoYc](https://community.konduit.ai/u/cqiaoYc)\ **Replies:** 3\ **Last updated:** [July 31, 2025, 10:41am UTC](https://community.konduit.ai/t/how-to-add-a-batchnorm-layer-after-a-1d-cnn-layer/3381 "2025-07-31T10:41:36Z")
How can I add a BatchNormalization layer after a 1D CNN layer? The BatchNormalization layer is designed for 2D CNNs by default, and adding it directly after a 1D CNN layer throws an error complaining about incompatible … --- ## [sun.misc.Unsafe and pom file](https://community.konduit.ai/t/sun-misc-unsafe-and-pom-file/3382)
**Author:** [@carlo8767](https://community.konduit.ai/u/carlo8767)\ **Replies:** 2\ **Last updated:** [July 31, 2025, 10:35am UTC](https://community.konduit.ai/t/sun-misc-unsafe-and-pom-file/3382 "2025-07-31T10:35:41Z")
Hello, I want to ask if there is any project that you are working for update the pom file with a java version more stable. I want to highlight how the use of native access exposes you project at possible memory leak a… --- ## [S01.oss.sonatype.org timeout](https://community.konduit.ai/t/s01-oss-sonatype-org-timeout/3379)
**Author:** [@Booker](https://community.konduit.ai/u/Booker)\ **Replies:** 6\ **Last updated:** [July 30, 2025, 8:34pm UTC](https://community.konduit.ai/t/s01-oss-sonatype-org-timeout/3379 "2025-07-30T20:34:09Z")
\[INFO\] e\[1m--------------------------------\[ war \]---------------------------------e\[m \[INFO\] Downloading from ossrh: https://s01.oss.sonatype.org/content/repositories/snapshots/org/eclipse/collections/eclipse-collectio… --- ## [Suggestions Thank you](https://community.konduit.ai/t/suggestions-thank-you/3378)
**Author:** [@MintakaB](https://community.konduit.ai/u/MintakaB)\ **Replies:** 1\ **Last updated:** [July 20, 2025, 10:21pm UTC](https://community.konduit.ai/t/suggestions-thank-you/3378 "2025-07-20T22:21:14Z")
Dear, I have an extensive application using DL4J and I have a few comments on the API to improve its integration. I am actually very happy with the performance and general approach to solve ML use cases on time series. … --- ## [Vectorizing with word2vec/paragraphvectors](https://community.konduit.ai/t/vectorizing-with-word2vec-paragraphvectors/3361)
**Author:** [@neyanog](https://community.konduit.ai/u/neyanog)\ **Replies:** 5\ **Last updated:** [July 4, 2025, 9:58am UTC](https://community.konduit.ai/t/vectorizing-with-word2vec-paragraphvectors/3361 "2025-07-04T09:58:58Z")
I need to vectorize text for multi-label classification and for this I thought about using Mulan (from what I read DL4J does not do multi-label classification). Is it possible to do vectorization using word2vec or paragr… --- ## [Can we trained a chat bot model using DL4J?](https://community.konduit.ai/t/can-we-trained-a-chat-bot-model-using-dl4j/3375)
**Author:** [@rajatpal](https://community.konduit.ai/u/rajatpal)\ **Replies:** 1\ **Last updated:** [July 4, 2025, 9:58am UTC](https://community.konduit.ai/t/can-we-trained-a-chat-bot-model-using-dl4j/3375 "2025-07-04T09:58:22Z")
Can we trained a chat bot model using DL4J ? --- ## [The new version can't be released?](https://community.konduit.ai/t/the-new-version-cant-be-released/3372)
**Author:** [@Booker](https://community.konduit.ai/u/Booker)\ **Replies:** 5\ **Last updated:** [July 4, 2025, 9:57am UTC](https://community.konduit.ai/t/the-new-version-cant-be-released/3372 "2025-07-04T09:57:10Z")
The new version can’t be released? --- ## [How to know if avx512 in using?](https://community.konduit.ai/t/how-to-know-if-avx512-in-using/3366)
**Author:** [@Booker](https://community.konduit.ai/u/Booker)\ **Replies:** 6\ **Last updated:** [June 17, 2025, 11:49am UTC](https://community.konduit.ai/t/how-to-know-if-avx512-in-using/3366 "2025-06-17T11:49:49Z")
09:04:36.249 \[main\] INFO org.nd4j.linalg.factory.Nd4jBackend – Loaded \[CpuBackend\] backend 09:04:36.578 \[main\] INFO org.nd4j.nativeblas.NativeOpsHolder – Number of threads used for linear algebra: 8 09:04:36.580 \[main\]… [Next page](https://community.konduit.ai/latest.md?page=1)