12 matching pages, found in 79 ms

Ask StyxWritten on your GPU machine; takes a few seconds the first time.

  1. forums.developer.nvidia.comhttps://forums.developer.nvidia.com › t › deepseek-v4-1-flash-on-4x-gb10… › 389220
    More about forums.developer.nvidia.com
    DeepSeek-V4.1-Flash on 4x GB10: 262K cold input in 27.3s, open-source runtime - DGX Spark / GB10 Projects - NVIDIA Developer Forums

    ForumNov 16, 2026. … 262,145 tokens of source code reached the first content in 27.28 seconds , with no prefix-cache hits. That is about 9,611 input tokens/s including frontend, tokenization and transport . For …

    0 points
  2. forums.developer.nvidia.comhttps://forums.developer.nvidia.com › t › velogb10-v0-7-0-release-qwen3-… › 384765
    More about forums.developer.nvidia.com
    veloGB10 v0.7.0 RELEASE - Qwen3.8-Flash-Next TP=2 @ 186 tok/sec , SINGLE at 137 tok/sec on code - DGX Spark / GB10 Projects - NVIDIA Developer Forums

    ForumSep 30, 2026. veloGB10 v0.7.0 RELEASE - Qwen3.8-Flash-Next TP=2 @ 186 tok/sec , SINGLE at 137 tok/sec on code Accelerated Computing DGX Spark / GB10 User Forum DGX Spark / GB10 Projects stav_kats September …

    0 points
  3. forums.developer.nvidia.comhttps://forums.developer.nvidia.com › t › nvfortran-26-9-wrong-code-cras… › 389378
    More about forums.developer.nvidia.com
    Nvfortran 26.9: wrong code / crashes with internal procedures (host association), OpenMP private array sections and MOVE_ALLOC - nvc, nvc++ and nvfortran - NVIDIA Developer Forums

    ForumNov 17, 2026. … a large Fortran CFD code (~130k lines) to nvfortran and OpenACC, we hit several wrong-code bugs that involve internal procedures or MOVE_ALLOC. Each one is reduced below to a small …

    0 points
  4. forums.developer.nvidia.comhttps://forums.developer.nvidia.com › t › deepseek-v4-1-flash-1017-exl3-… › 386125
    More about forums.developer.nvidia.com
    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 - DGX Spark / GB10 - NVIDIA Developer Forums

    ForumOct 18, 2026. … s 56.8 2.1x Decode, code 39.9 tok/s 92.2 2.3x Needle in 64K 80.4 s 35.9 s 2.2x 4 requests, code, total 1 at a time 140 tok/s Prompt cache: 2nd …

    0 points
  5. forums.developer.nvidia.comhttps://forums.developer.nvidia.com › t › nvbufsurface-memory-leak-and-t… › 389372
    More about forums.developer.nvidia.com
    NvBufSurface memory leak and timestamp drift in multi-stream RTSP DeepStream 7.0 pipeline on Jetson Orin Nano - DeepStream SDK - NVIDIA Developer Forums

    ForumNov 17, 2026. … pyservicemaker, The similar pipeline code is pyservicemaker deepstream_test3.py Related topics Topic Replies Views Activity Significant Memory leak when streaming from a clients RTSP source DeepStream SDK gstreamer , nvbugs 11 3020 August …

    0 points
  6. forums.developer.nvidia.comhttps://forums.developer.nvidia.com › t › deepseek-v4-1-flash-on-4x-dgx-… › 389371
    More about forums.developer.nvidia.com
    DeepSeek-V4.1-Flash on 4x DGX Spark GB10 (CX7 ring): full setup + cold prefill & decode numbers up to 1M context - DGX Spark / GB10 Projects - NVIDIA Developer Forums

    ForumNov 17, 2026. … reported ~9.6K @ 262K on source-code input, against ~8.1K here on CJK input. Its 1M figure is a synthetic capacity check rather than a same-corpus prefill sweep, so no comparable long …

    0 points
  7. forums.developer.nvidia.comhttps://forums.developer.nvidia.com › t › use-nvidia-nemo-to-turn-agent-… › 387996
    More about forums.developer.nvidia.com
    Use NVIDIA NeMo to Turn Agent Failures into Tests and Harness Fixes - Technical Blog - NVIDIA Developer Forums

    ForumNov 4, 2026. … 28, 2025 Improve AI Code Generation Using NVIDIA AgentIQ Open-Source Toolkit Technical Blog agentic-ai 1 398 April 10, 2025 NVIDIA Agent Intelligence toolkit is now the NVIDIA NeMo Agent toolkit …

    0 points
  8. forums.developer.nvidia.comhttps://forums.developer.nvidia.com › t › rtx-spark-on-windows-cuda-allo… › 386453
    More about forums.developer.nvidia.com
    RTX Spark on Windows: CUDA allocations consume system commit even with 96 GiB dedicated GPU memory - RTX Spark (NEW) - NVIDIA Developer Forums

    ForumOct 21, 2026. … minimal CUDA C reproduction code and measurement logs if needed. Thanks! Native vLLM for RTX Spark on Windows ARM64 (w/Qwen3.8-Flash-Next-FP4-Local) aureliusvalerius00 October 23, 2026, 7:58am 2 …

    0 points
  9. forums.developer.nvidia.comhttps://forums.developer.nvidia.com › t › nvc-26-9-argument-dependent-lo… › 389494
    More about forums.developer.nvidia.com
    Nvc++26.9: argument-dependent lookup inside a generic lambda misses functions declared after the enclosing template - nvc, nvc++ and nvfortran - NVIDIA Developer Forums

    ForumNov 18, 2026. … comparison; it accepts the code Ubuntu 24.04.4 LTS, x86_64, glibc 2.39 Reproducer // repro.cpp #include <iostream> namespace lib { template <typename T> void call(const T& x) { [&](auto) { f(x); }(0); } } // namespace lib …

    0 points
  10. forums.developer.nvidia.comhttps://forums.developer.nvidia.com › t › deepstream-9-licensing › 388844
    More about forums.developer.nvidia.com
    Deepstream 9.* licensing - DeepStream SDK - NVIDIA Developer Forums

    ForumNov 12, 2026. … 9.2. And the most source codes of DeepStream have been open sourced. The open source DeepStream license is DeepStream/LICENSE at main · NVIDIA/DeepStream saju November 18, 2026, 6:18am 4 Thanks …

    0 points

Search for “Source Code site:forums.developer.nvidia.com” on Google, or add !ddg, !w and other shortcuts to any search.