sm121

Here are 4 public repositories matching this topic...

Docker containers for AI models on NVIDIA DGX Spark (GB10, SM121, aarch64). TurboQuant KV cache compression + mamba-ssm aarch64 build.

aarch64 blackwell kv-cache vllm nvfp4 dgx-spark mamba-ssm sm121 turboquant

DGX Spark (GB10/SM121) platform support for Meta's KernelAgent — auto-detect, hardware constraints, safe Triton configs

cuda nvidia triton gpu-optimization gb10 dgx-spark sm121 kernel-agent

Run Qwen3.5-122B on a single NVIDIA GB10 with NVFP4 weights + TurboQuant 3.5-bit KV cache. Built on vLLM v0.16 with custom Triton kernels for SM121.

triton moe quantization blackwell kv-cache vllm local-llm llm-inference qwen3 nvfp4 sm121 turboquant nvidia-gb10

Pre-built PyTorch wheels and build scripts for NVIDIA DGX Spark (GB10, sm_121, Blackwell, CUDA 13.0, ARM64)

machine-learning deep-learning gpu cuda inference pytorch nvidia arm64 aarch64 fine-tuning blackwell llm gb10 dgx-spark grace-blackwell sm121 cuda-13 pre-built-wheels

Add a description, image, and links to the sm121 topic page so that developers can more easily learn about it.

To associate your repository with the sm121 topic, visit your repo's landing page and select "manage topics."