# Latest **URL:** https://forums.developer.nvidia.com/latest.md [Latest](https://forums.developer.nvidia.com/latest.md) · [Categories](https://forums.developer.nvidia.com/categories.md) · [Tags](https://forums.developer.nvidia.com/tags.md) --- ## [The way to prepare for GTC Berlin 2026](https://forums.developer.nvidia.com/t/the-way-to-prepare-for-gtc-berlin-2026/386296)
**Author:** [@MarkusHoHo](https://forums.developer.nvidia.com/u/MarkusHoHo)\ **Replies:** 0\ **Last updated:** [October 19, 2026, 8:31am UTC](https://forums.developer.nvidia.com/t/the-way-to-prepare-for-gtc-berlin-2026/386296 "2026-10-19T08:31:53Z")
Can’t make it to #NVIDIAGTC Berlin? We’ve got you covered. Join us for 3 days of livestreams covering the biggest moments of the week, from the keynote recap to real-world AI demos and developer stories straight from B… --- ## [PyNvVideoCodec 2.2 is released](https://forums.developer.nvidia.com/t/pynvvideocodec-2-2-is-released/380856)
**Author:** [@mandar\_godse](https://forums.developer.nvidia.com/u/mandar_godse)\ **Replies:** 4\ **Last updated:** [September 16, 2026, 10:24am UTC](https://forums.developer.nvidia.com/t/pynvvideocodec-2-2-is-released/380856 "2026-09-16T10:24:00Z")
We are pleased to announce the release of PyNvVideoCodec 2.2, the latest version of our GPU-accelerated Python library for video decoding, encoding, and transcoding , all with the simplicity and flexibility of Python. P… --- ## [Introducing NVIDIA NemoClaw](https://forums.developer.nvidia.com/t/introducing-nvidia-nemoclaw/363701)
**Author:** [@rjensen](https://forums.developer.nvidia.com/u/rjensen)\ **Replies:** 0\ **Last updated:** [March 16, 2026, 8:22pm UTC](https://forums.developer.nvidia.com/t/introducing-nvidia-nemoclaw/363701 "2026-03-16T20:22:22Z")
NVIDIA NemoClaw is an open source stack that simplifies running OpenClaw always-on assistants more safely, with a single command. It installs the NVIDIA OpenShell runtime, part of the NVIDIA Agent Toolkit, a secure envir… --- ## [Open a Support Case for DLI Issues](https://forums.developer.nvidia.com/t/open-a-support-case-for-dli-issues/345829)
**Author:** [@TomNVIDIA](https://forums.developer.nvidia.com/u/TomNVIDIA)\ **Replies:** 0\ **Last updated:** [September 23, 2025, 2:37pm UTC](https://forums.developer.nvidia.com/t/open-a-support-case-for-dli-issues/345829 "2025-09-23T14:37:14Z")
For DLI Course assistance, please visit the DLI Support Page to open a support case. This ensures your request is directed to the appropriate team for timely and accurate support. When submitting your case, please make … --- ## [DeepSeek-V4.1-Flash-1017 (EXL3 2.9bpw) on 2x DGX Spark with TensorFold: 57 tok/s text, 92 tok/s code, 2.1-2.3x the vLLM kit](https://forums.developer.nvidia.com/t/deepseek-v4-1-flash-1017-exl3-2-9bpw-on-2x-dgx-spark-with-tensorfold-57-tok-s-text-92-tok-s-code-2-1-2-3x-the-vllm-kit/386125)
**Author:** [@Elevatormusic](https://forums.developer.nvidia.com/u/Elevatormusic)\ **Replies:** 128\ **Last updated:** [October 22, 2026, 12:38am UTC](https://forums.developer.nvidia.com/t/deepseek-v4-1-flash-1017-exl3-2-9bpw-on-2x-dgx-spark-with-tensorfold-57-tok-s-text-92-tok-s-code-2-1-2-3x-the-vllm-kit/386125 "2026-10-22T00:38:40Z")
DeepSeek-V4.1-Flash-1017 (EXL3 2.9 bpw, 1M context) on 2x DGX Spark, TP=2 over the CX7 cable. Recipe Github: GitHub - Elevatormusic/DeepSeek-V4.1-Flash-1017-EXL3-TensorFold-2x-DGX-Spark: DeepSeek-V4.1-Flash-1017 EXL3 2… --- ## [DGX Spark: Could Windows on ARM Support Be Possible, Like RTX Spark, N1X?](https://forums.developer.nvidia.com/t/dgx-spark-could-windows-on-arm-support-be-possible-like-rtx-spark-n1x/371870)
**Author:** [@PILCOTHINK](https://forums.developer.nvidia.com/u/PILCOTHINK)\ **Replies:** 63\ **Last updated:** [October 22, 2026, 12:30am UTC](https://forums.developer.nvidia.com/t/dgx-spark-could-windows-on-arm-support-be-possible-like-rtx-spark-n1x/371870 "2026-10-22T00:30:33Z")
Hello, Recently, I feel like I’ve been seeing a lot of articles about the N1/N1X series. What particularly stood out to me is that they seem to support Windows on ARM. I think I read somewhere that the N1 series and DG… --- ## [Inquiry Regarding Jetson Thor (T5000) Boot Failure](https://forums.developer.nvidia.com/t/inquiry-regarding-jetson-thor-t5000-boot-failure/385938)
**Author:** [@andy.chung](https://forums.developer.nvidia.com/u/andy.chung)\ **Replies:** 25\ **Last updated:** [October 22, 2026, 12:17am UTC](https://forums.developer.nvidia.com/t/inquiry-regarding-jetson-thor-t5000-boot-failure/385938 "2026-10-22T00:17:54Z")
Dear Support Team, We have developed a custom carrier board for the Jetson Thor (T5000) and are currently performing bring-up activities. However, we are experiencing a boot failure and have been investigating the power… --- ## [Flare - NVIDIA's new inference server in Rust](https://forums.developer.nvidia.com/t/flare-nvidias-new-inference-server-in-rust/386436)
**Author:** [@Digital\_David](https://forums.developer.nvidia.com/u/Digital_David)\ **Replies:** 21\ **Last updated:** [October 22, 2026, 12:11am UTC](https://forums.developer.nvidia.com/t/flare-nvidias-new-inference-server-in-rust/386436 "2026-10-22T00:11:35Z")
NVIDIA-AI just quietly dropped its own local inference server… No announcement. Single-digit stars It’s called Flare and Apache 2.0 Built for SM120/SM121 GPUs RTX PRO 6000 Blackwell and DGX Spark PyTorch + FlashInfe… --- ## [Isaac Sim 6.2 General Availability](https://forums.developer.nvidia.com/t/isaac-sim-6-2-general-availability/386512)
**Author:** [@rthaker](https://forums.developer.nvidia.com/u/rthaker)\ **Replies:** 0\ **Last updated:** [October 22, 2026, 12:10am UTC](https://forums.developer.nvidia.com/t/isaac-sim-6-2-general-availability/386512 "2026-10-22T00:10:07Z")
Isaac Sim 6.2 GA Isaac Sim 6.2 is available! This is primarily a bug-fix release, delivered to support Isaac Lab 3.0 GA. Building on 6.1, it focuses on simulation consistency and reliability, with targeted improvements t… --- ## [How to Set Up DGX Spark for Headless Access Using ThinLinc (VDI / Linux Remote Desktop)](https://forums.developer.nvidia.com/t/how-to-set-up-dgx-spark-for-headless-access-using-thinlinc-vdi-linux-remote-desktop/386478)
**Author:** [@hitjethva81](https://forums.developer.nvidia.com/u/hitjethva81)\ **Replies:** 1\ **Last updated:** [October 21, 2026, 11:56pm UTC](https://forums.developer.nvidia.com/t/how-to-set-up-dgx-spark-for-headless-access-using-thinlinc-vdi-linux-remote-desktop/386478 "2026-10-21T23:56:03Z")
NVIDIA DGX Spark is a compact AI system designed for AI development, inference, and GPU-accelerated workloads. While you can manage the system using SSH, some workloads require a complete graphical Linux desktop. ThinLi… --- ## [FW upgrade fail](https://forums.developer.nvidia.com/t/fw-upgrade-fail/386507)
**Author:** [@dgxspark](https://forums.developer.nvidia.com/u/dgxspark)\ **Replies:** 5\ **Last updated:** [October 21, 2026, 11:54pm UTC](https://forums.developer.nvidia.com/t/fw-upgrade-fail/386507 "2026-10-21T23:54:38Z")
There’s new firmware available for the FE Spark, but upgrade fails with: ╔══════════════════════════════════════════════════════════════════════════════╗ ║ Upgrade Embedded Controller from 0x03000508 to 0x03000d07? … --- ## [GLM-5.3-Flash: 320B total parameters / 18B active](https://forums.developer.nvidia.com/t/glm-5-3-flash-320b-total-parameters-18b-active/381350)
**Author:** [@co-le](https://forums.developer.nvidia.com/u/co-le)\ **Replies:** 882\ **Last updated:** [October 21, 2026, 11:29pm UTC](https://forums.developer.nvidia.com/t/glm-5-3-flash-320b-total-parameters-18b-active/381350 "2026-10-21T23:29:46Z")
Better than GLM-5.2 Will wait for 4bit quants, very interesting --- ## [UE5.7.4 DLSS4.5 NIS plugin ver 8.7.2 - NIS\_Scaler.h - Pixels-wide screen border corruption for arbitrary resolutions](https://forums.developer.nvidia.com/t/ue5-7-4-dlss4-5-nis-plugin-ver-8-7-2-nis-scaler-h-pixels-wide-screen-border-corruption-for-arbitrary-resolutions/386511)
**Author:** [@dusit.e](https://forums.developer.nvidia.com/u/dusit.e)\ **Replies:** 0\ **Last updated:** [October 21, 2026, 11:23pm UTC](https://forums.developer.nvidia.com/t/ue5-7-4-dlss4-5-nis-plugin-ver-8-7-2-nis-scaler-h-pixels-wide-screen-border-corruption-for-arbitrary-resolutions/386511 "2026-10-21T23:23:15Z")
In UE, you can resize your PIE window as you please, so arbitrary resolutions are possible Earlier this month (Oct 2026), in the process of upgrading from UE5.6.1 to UE5.7.4 (and boosting ourselves up to DLSS4.5 for UE5… --- ## [Request to Increase NVIDIA NIM API Rate Limit to 200 RPM](https://forums.developer.nvidia.com/t/request-to-increase-nvidia-nim-api-rate-limit-to-200-rpm/386510)
**Author:** [@ieiian1](https://forums.developer.nvidia.com/u/ieiian1)\ **Replies:** 0\ **Last updated:** [October 21, 2026, 11:22pm UTC](https://forums.developer.nvidia.com/t/request-to-increase-nvidia-nim-api-rate-limit-to-200-rpm/386510 "2026-10-21T23:22:33Z")
Hello NVIDIA Support Team, I am writing to request an increase in the free rate limit for the NVIDIA NIM API. My account and application details are as follows: Account email: ieiian@protonmail.com API Key prefix: nva… --- ## [DGX Spark headless setup desktop solution w/BIOS access](https://forums.developer.nvidia.com/t/dgx-spark-headless-setup-desktop-solution-w-bios-access/386509)
**Author:** [@mopace](https://forums.developer.nvidia.com/u/mopace)\ **Replies:** 0\ **Last updated:** [October 21, 2026, 10:00pm UTC](https://forums.developer.nvidia.com/t/dgx-spark-headless-setup-desktop-solution-w-bios-access/386509 "2026-10-21T22:00:10Z")
i was able to pair the DGX Spark with a TinyPilot voyager 3 (kvm over IP) successfully. The HDMI cable that came with the voyager seems to work well. I did have to purchase a USB-IF Certified 10GB Gen 2 USB-C to USB-… --- ## [Jetson Orin NX Thermal Design Volume](https://forums.developer.nvidia.com/t/jetson-orin-nx-thermal-design-volume/386427)
**Author:** [@griggs](https://forums.developer.nvidia.com/u/griggs)\ **Replies:** 4\ **Last updated:** [October 21, 2026, 9:56pm UTC](https://forums.developer.nvidia.com/t/jetson-orin-nx-thermal-design-volume/386427 "2026-10-21T21:56:08Z")
I am having difficulty interpreting the downloadable Jetson Orin NX thermal design volume from the developer site. I have a physical module in hand, specifically the 900-13767-0000-001 - Jetson Orin NX 16GB version and … --- ## [Black screen with fullscreen applications after suspend with VRR enabled on Wayland](https://forums.developer.nvidia.com/t/black-screen-with-fullscreen-applications-after-suspend-with-vrr-enabled-on-wayland/357570)
**Author:** [@rexpulli](https://forums.developer.nvidia.com/u/rexpulli)\ **Replies:** 11\ **Last updated:** [October 21, 2026, 9:23pm UTC](https://forums.developer.nvidia.com/t/black-screen-with-fullscreen-applications-after-suspend-with-vrr-enabled-on-wayland/357570 "2026-10-21T21:23:36Z")
I am reporting a reproducible issue on GNOME Wayland where all fullscreen applications (video players, games, vkcube) display a black screen after the system resumes from a suspend cycle. It only happens when VRR is enab… --- ## [DGX Spark hardware fault confirmed, but manufacturer warranty declined](https://forums.developer.nvidia.com/t/dgx-spark-hardware-fault-confirmed-but-manufacturer-warranty-declined/386465)
**Author:** [@dylanlz](https://forums.developer.nvidia.com/u/dylanlz)\ **Replies:** 2\ **Last updated:** [October 21, 2026, 9:19pm UTC](https://forums.developer.nvidia.com/t/dgx-spark-hardware-fault-confirmed-but-manufacturer-warranty-declined/386465 "2026-10-21T21:19:20Z")
I have been reading the shutdown threads here and wanted to share what happened after I went through the diagnostic and support process. I am based in Singapore and bought my NVIDIA DGX Spark new through a third-party s… --- ## [DGXSPARK temperature too high, automatic shutdown。](https://forums.developer.nvidia.com/t/dgxspark-temperature-too-high-automatic-shutdown/363370)
**Author:** [@hongde](https://forums.developer.nvidia.com/u/hongde)\ **Replies:** 206\ **Last updated:** [October 21, 2026, 9:16pm UTC](https://forums.developer.nvidia.com/t/dgxspark-temperature-too-high-automatic-shutdown/363370 "2026-10-21T21:16:30Z")
Room temperature is 18 degrees, DGXSPARK running COMFYUI to generate video (about 10 minutes), often turns off automatically due to overheating. Now I dare not use COMFYUI, how to set the cooling fan. --- ## [\[Thor DevKit\] Inquiring on Current Monitoring Architecture: Threshold levels, alert mechanisms, and trigger currents](https://forums.developer.nvidia.com/t/thor-devkit-inquiring-on-current-monitoring-architecture-threshold-levels-alert-mechanisms-and-trigger-currents/386468)
**Author:** [@eric.ch.chen](https://forums.developer.nvidia.com/u/eric.ch.chen)\ **Replies:** 1\ **Last updated:** [October 21, 2026, 9:04pm UTC](https://forums.developer.nvidia.com/t/thor-devkit-inquiring-on-current-monitoring-architecture-threshold-levels-alert-mechanisms-and-trigger-currents/386468 "2026-10-21T21:04:52Z")
Hi , Following up on our carrier board design for the Jetson AGX Thor SOM, we would like to better understand the detailed operating mechanism and threshold limits of the onboard current/power monitor ICs (e.g., INA ser… --- ## [AGX Thor T5000 QSFP28 10G TX/RX eye digram Test](https://forums.developer.nvidia.com/t/agx-thor-t5000-qsfp28-10g-tx-rx-eye-digram-test/386392)
**Author:** [@rain1\_wang](https://forums.developer.nvidia.com/u/rain1_wang)\ **Replies:** 4\ **Last updated:** [October 21, 2026, 9:00pm UTC](https://forums.developer.nvidia.com/t/agx-thor-t5000-qsfp28-10g-tx-rx-eye-digram-test/386392 "2026-10-21T21:00:45Z")
Hi Nivdia engineer 1.Could you please inform me if NVIDIA has tested the 25G and 10G TX/RX eye diagrams of QSFP28?How was it verified? 2.Keysight only has the eye diagram test program for TX, but not for RX. We would l… --- ## [RTX 5090 + Samsung ViewFinity S9 5K: Signal Loss / Black Screen on all drivers after 576.88](https://forums.developer.nvidia.com/t/rtx-5090-samsung-viewfinity-s9-5k-signal-loss-black-screen-on-all-drivers-after-576-88/368789)
**Author:** [@erenozturk](https://forums.developer.nvidia.com/u/erenozturk)\ **Replies:** 23\ **Last updated:** [October 21, 2026, 8:52pm UTC](https://forums.developer.nvidia.com/t/rtx-5090-samsung-viewfinity-s9-5k-signal-loss-black-screen-on-all-drivers-after-576-88/368789 "2026-10-21T20:52:15Z")
Description: System specs: GPU: NVIDIA GeForce RTX 5090 Monitor: Samsung ViewFinity S9 (5K, 5120x2880) OS: Windows 11 / Ubuntu No diference Connection: DisplayPort Issue: On any driver newer than 576.88, the monitor… --- ## [Does NVIDIA Grace SCF Implement Per-Node/Link Hardware Performance Counters?](https://forums.developer.nvidia.com/t/does-nvidia-grace-scf-implement-per-node-link-hardware-performance-counters/386378)
**Author:** [@bxc8802](https://forums.developer.nvidia.com/u/bxc8802)\ **Replies:** 2\ **Last updated:** [October 21, 2026, 8:50pm UTC](https://forums.developer.nvidia.com/t/does-nvidia-grace-scf-implement-per-node-link-hardware-performance-counters/386378 "2026-10-21T20:50:55Z")
Hi, NVIDIA Team, Does the NVIDIA Grace Scalable Coherency Fabric (SCF) physically implement independent hardware performance counters at individual Cache Switch Nodes (CSNs), internal mesh ports, or CSN-to-CSN links for… --- ## [404 Error / Missing API Endpoint Code for cosmos3-nano on build.nvidia.com](https://forums.developer.nvidia.com/t/404-error-missing-api-endpoint-code-for-cosmos3-nano-on-build-nvidia-com/372044)
**Author:** [@anubhavrai100](https://forums.developer.nvidia.com/u/anubhavrai100)\ **Replies:** 9\ **Last updated:** [October 21, 2026, 8:47pm UTC](https://forums.developer.nvidia.com/t/404-error-missing-api-endpoint-code-for-cosmos3-nano-on-build-nvidia-com/372044 "2026-10-21T20:47:52Z")
Hi NVIDIA Team, I am trying to test the newly released cosmos3-nano model using the free cloud credits on build.nvidia.com. The model page UI indicates that it is available as a free cloud endpoint, but the actual inte… --- ## [GPU resource calculator](https://forums.developer.nvidia.com/t/gpu-resource-calculator/289761)
**Author:** [@HCAKIRLI](https://forums.developer.nvidia.com/u/HCAKIRLI)\ **Replies:** 8\ **Last updated:** [October 21, 2026, 8:17pm UTC](https://forums.developer.nvidia.com/t/gpu-resource-calculator/289761 "2026-10-21T20:17:43Z")
Is there a calculation tool that can help us determine the exact “cuda core” resource we need when we do real-time work in the customer location environment? example; Mistral 7b LLM model, There will be a maximum of… --- ## [Memory clarification issue on DGX station - 1T LLM model possible?](https://forums.developer.nvidia.com/t/memory-clarification-issue-on-dgx-station-1t-llm-model-possible/368919)
**Author:** [@Digital\_David](https://forums.developer.nvidia.com/u/Digital_David)\ **Replies:** 17\ **Last updated:** [October 21, 2026, 8:02pm UTC](https://forums.developer.nvidia.com/t/memory-clarification-issue-on-dgx-station-1t-llm-model-possible/368919 "2026-10-21T20:02:35Z")
Good Day, Having lived through the DGX Spark model size issue, I would like to get some clarification of the up to 1T parameter model size claim for the DGX Station . At FP4, a 1.T model would require ~500-600GB + overh… --- ## [Is there any way to find Physical location through the logical SM IDs?](https://forums.developer.nvidia.com/t/is-there-any-way-to-find-physical-location-through-the-logical-sm-ids/383978)
**Author:** [@easyhyum](https://forums.developer.nvidia.com/u/easyhyum)\ **Replies:** 1\ **Last updated:** [October 21, 2026, 7:57pm UTC](https://forums.developer.nvidia.com/t/is-there-any-way-to-find-physical-location-through-the-logical-sm-ids/383978 "2026-10-21T19:57:44Z")
I’m trying to understand how logical SM IDs (as reported by the PTX %smid register) map to the physical placement of SMs on the die — specifically on Blackwell parts such as B200 and the RTX PRO 6000 Server Edition (GB20… --- ## [Is there a way to emulate a VB1940 camera with an FPGA using SIPL?](https://forums.developer.nvidia.com/t/is-there-a-way-to-emulate-a-vb1940-camera-with-an-fpga-using-sipl/386508)
**Author:** [@joe\_schmo](https://forums.developer.nvidia.com/u/joe_schmo)\ **Replies:** 0\ **Last updated:** [October 21, 2026, 7:51pm UTC](https://forums.developer.nvidia.com/t/is-there-a-way-to-emulate-a-vb1940-camera-with-an-fpga-using-sipl/386508 "2026-10-21T19:51:10Z")
I am trying to emulate a VB1940 camera using an FPGA and I am encountering the following error when I try to run the sipl\_player.py HSB example… Is the problem related to it trying to configure a camera that doesn’t … --- ## [\`sudo reboot now\` and Spark doesn't come back.. started after installing updates today](https://forums.developer.nvidia.com/t/sudo-reboot-now-and-spark-doesnt-come-back-started-after-installing-updates-today/386495)
**Author:** [@DannyTup](https://forums.developer.nvidia.com/u/DannyTup)\ **Replies:** 4\ **Last updated:** [October 21, 2026, 7:43pm UTC](https://forums.developer.nvidia.com/t/sudo-reboot-now-and-spark-doesnt-come-back-started-after-installing-updates-today/386495 "2026-10-21T19:43:58Z")
I installed all updates today, and when I rebooted afterwards, the box never came back. So I attached a monitor and pressed the power button, then after a few minutes of nothing (it was probably off), pressed it again. … --- ## [The CUDA 13.4 nvcc compiler still cannot enable the C++23 standard on Windows](https://forums.developer.nvidia.com/t/the-cuda-13-4-nvcc-compiler-still-cannot-enable-the-c-23-standard-on-windows/381009)
**Author:** [@zy\_ih](https://forums.developer.nvidia.com/u/zy_ih)\ **Replies:** 4\ **Last updated:** [October 21, 2026, 7:43pm UTC](https://forums.developer.nvidia.com/t/the-cuda-13-4-nvcc-compiler-still-cannot-enable-the-c-23-standard-on-windows/381009 "2026-10-21T19:43:01Z")
Problem Description According to the official NVIDIA documentation, nvcc supports the C++23 standard, which can be enabled simply by adding the compilation option --std=c++23. However, in a Windows environment, this opti… [Next page](https://forums.developer.nvidia.com/latest.md?page=1)