{
  "schema_version": 1,
  "description": "Complementary kernel knowledge map for Humanize-driven GPU kernel optimization. Lists code and knowledge repositories that have no curated PR diffs in the local Route A corpus (NVIDIA developer samples, Colfax research kernels, simveit micro-tutorials, Hygon/DCU optimization references, and open Triton kernel libraries such as AITER, AOTriton, Conch, FlagGems, Liger Kernel, Hugging Face kernels, and Triton-distributed); each framework entry points to upstream repos, kernel directories, and source guides. Topic entries map kernel topics to per-framework references for live clone/grep workflows. Frameworks already covered by Route A PR bundles (SGLang, vLLM, TensorRT-LLM, PyTorch, FlashAttention, FlashInfer, CUTLASS/CuTe, CCCL, Triton, DeepGEMM, ThunderKittens, TileLang, QuACK, DeepSeek TileKernels) are intentionally excluded.",
  "frameworks": [
    {
      "id": "nvidia-code-samples",
      "name": "NVIDIA Developer Code Samples",
      "repo": "NVIDIA-developer-blog/code-samples",
      "url": "https://github.com/NVIDIA-developer-blog/code-samples",
      "kernel_paths": [
        "posts",
        "Samples",
        "src",
        "README.md"
      ],
      "tags": [
        "cuda-samples",
        "gemm",
        "transpose",
        "coalescing",
        "shared-memory",
        "bank-conflicts",
        "reduction",
        "occupancy"
      ]
    },
    {
      "id": "simveit-effective-transpose",
      "name": "simveit effective_transpose",
      "repo": "simveit/effective_transpose",
      "url": "https://github.com/simveit/effective_transpose",
      "kernel_paths": [
        ".",
        "src",
        "examples",
        "README.md"
      ],
      "tags": [
        "cute-dsl",
        "quack",
        "gemm",
        "tma",
        "wgmma",
        "swizzle",
        "transpose",
        "rmsnorm",
        "block-scaled",
        "nvfp4",
        "gdn",
        "hopper",
        "blackwell"
      ]
    },
    {
      "id": "simveit-load-and-store",
      "name": "simveit load_and_store",
      "repo": "simveit/load_and_store",
      "url": "https://github.com/simveit/load_and_store",
      "kernel_paths": [
        ".",
        "src",
        "examples",
        "README.md"
      ],
      "tags": [
        "cute-dsl",
        "load-store",
        "gemm",
        "tma",
        "wgmma",
        "shared-memory",
        "hopper",
        "blackwell"
      ]
    },
    {
      "id": "colfax-article-src",
      "name": "Colfax article source kernels",
      "repo": "ColfaxResearch/cfx-article-src",
      "url": "https://github.com/ColfaxResearch/cfx-article-src",
      "kernel_paths": [
        "tma",
        "pipeline-gemm",
        "streamk",
        "transpose-cute",
        "cutlass_gemm"
      ],
      "tags": [
        "cutlass",
        "cute",
        "cute-dsl",
        "gemm",
        "attention",
        "tma",
        "wgmma",
        "stream-k",
        "persistent",
        "transpose",
        "block-scaled",
        "blackwell",
        "hopper"
      ]
    },
    {
      "id": "colfax-cutlass-kernels",
      "name": "Colfax CUTLASS kernels",
      "repo": "ColfaxResearch/cutlass-kernels",
      "url": "https://github.com/ColfaxResearch/cutlass-kernels",
      "kernel_paths": [
        "src",
        "lib/gemm",
        "include",
        "examples",
        "README.md"
      ],
      "tags": [
        "cutlass",
        "cute",
        "gemm",
        "tma",
        "wgmma",
        "stream-k",
        "persistent",
        "blackwell",
        "hopper"
      ]
    },
    {
      "id": "hygon-hip-kernel-optimizer",
      "name": "Hygon HIP Kernel Optimizer Skill",
      "repo": "yuguo-Jack/cuda-optimized-skill",
      "url": "https://github.com/yuguo-Jack/cuda-optimized-skill",
      "kernel_paths": [
        "skills/hygon-hip-kernel-optimizer/SKILL.md",
        "skills/hygon-hip-kernel-optimizer/references/optimization_catalog.md",
        "skills/hygon-hip-kernel-optimizer/references/dcu_metrics_guide.md",
        "skills/hygon-hip-kernel-optimizer/references/method_registry.json",
        "skills/hygon-hip-kernel-optimizer/references/dcu_isa_signatures.json",
        "skills/hygon-hip-kernel-optimizer/examples/walkthrough.md"
      ],
      "tags": [
        "dcu",
        "hygon",
        "hip",
        "rocm",
        "ck-tile",
        "mmac",
        "wave64",
        "hipprof",
        "dccobjdump",
        "sqtt"
      ]
    },
    {
      "id": "rocm-aiter",
      "name": "AITER AI Tensor Engine for ROCm",
      "repo": "ROCm/aiter",
      "url": "https://github.com/ROCm/aiter",
      "kernel_paths": [
        "aiter",
        "op_tests",
        "docs",
        "gradlib",
        "csrc",
        "requirements-triton-comms.txt",
        ".github/scripts/install_triton.sh",
        "README.md"
      ],
      "tags": [
        "triton",
        "rocm",
        "aiter",
        "attention",
        "mla",
        "paged-attention",
        "fused-moe",
        "gemm",
        "rmsnorm",
        "quantization",
        "communication"
      ]
    },
    {
      "id": "rocm-aotriton",
      "name": "AOTriton Ahead-of-Time Triton Math Library",
      "repo": "ROCm/aotriton",
      "url": "https://github.com/ROCm/aotriton",
      "kernel_paths": [
        "v2python",
        "v2src",
        "v3python",
        "v3src",
        "tritonsrc",
        "include/aotriton",
        "test",
        "docs",
        "README.md"
      ],
      "tags": [
        "triton",
        "rocm",
        "aot",
        "aotriton",
        "flash-attention",
        "sdpa",
        "attention",
        "compiler",
        "codegen"
      ]
    },
    {
      "id": "stackav-conch",
      "name": "Conch Triton Kernel Standard Library",
      "repo": "stackav-oss/conch",
      "url": "https://github.com/stackav-oss/conch",
      "kernel_paths": [
        "conch",
        "tests",
        "benchmarks",
        "README.md",
        "pyproject.toml"
      ],
      "tags": [
        "triton",
        "rocm",
        "standard-library",
        "paged-attention",
        "varlen-attention",
        "rmsnorm",
        "rotary",
        "kv-cache",
        "fp8",
        "int8",
        "quantization",
        "vllm"
      ]
    },
    {
      "id": "flaggems",
      "name": "FlagGems Triton Operator Library",
      "repo": "flagos-ai/FlagGems",
      "url": "https://github.com/flagos-ai/FlagGems",
      "kernel_paths": [
        "src/flag_gems",
        "benchmark",
        "tests",
        "modules_tests",
        "experimental_tests",
        "triton_src",
        "docs",
        "README.md"
      ],
      "tags": [
        "triton",
        "pytorch",
        "operator-library",
        "llm",
        "backend-neutral",
        "multi-backend",
        "aten",
        "normalization",
        "reduction",
        "elementwise",
        "quantization"
      ]
    },
    {
      "id": "liger-kernel",
      "name": "Liger Kernel Triton Kernels for LLM Training",
      "repo": "linkedin/Liger-Kernel",
      "url": "https://github.com/linkedin/Liger-Kernel",
      "kernel_paths": [
        "src/liger_kernel",
        "test",
        "benchmark",
        "examples",
        "docs",
        "README.md"
      ],
      "tags": [
        "triton",
        "llm-training",
        "rmsnorm",
        "rope",
        "swiglu",
        "cross-entropy",
        "fused-linear-cross-entropy",
        "loss",
        "amd"
      ]
    },
    {
      "id": "huggingface-kernels",
      "name": "Hugging Face Kernels and kernels-community Hub",
      "repo": "huggingface/kernels",
      "url": "https://github.com/huggingface/kernels",
      "kernel_paths": [
        "src",
        "kernel-builder",
        "tests",
        "README.md",
        "https://huggingface.co/kernels",
        "https://huggingface.co/kernels-community"
      ],
      "tags": [
        "triton",
        "kernel-hub",
        "kernels-community",
        "paged-attention",
        "triton-moe",
        "triton-scaled-mm",
        "rmsnorm",
        "rotary",
        "quantization"
      ]
    },
    {
      "id": "triton-distributed",
      "name": "Triton-distributed",
      "repo": "ByteDance-Seed/Triton-distributed",
      "url": "https://github.com/ByteDance-Seed/Triton-distributed",
      "kernel_paths": [
        "python",
        "lib",
        "include",
        "csrc",
        "docs",
        "tests",
        "README.md"
      ],
      "tags": [
        "triton",
        "distributed",
        "communication-overlap",
        "gemm-allreduce",
        "allgather-gemm",
        "reduce-scatter",
        "moe",
        "flash-decode",
        "amd",
        "nvidia"
      ]
    }
  ],
  "topics": [
    {
      "id": "attention",
      "name": "Attention / FMHA / Paged",
      "applies_to": [
        "simveit-effective-transpose",
        "simveit-load-and-store",
        "colfax-article-src",
        "colfax-cutlass-kernels",
        "hygon-hip-kernel-optimizer",
        "rocm-aiter",
        "rocm-aotriton",
        "stackav-conch",
        "huggingface-kernels",
        "triton-distributed"
      ],
      "tags": [
        "attention",
        "fmha",
        "paged",
        "kv-cache",
        "softmax",
        "online"
      ]
    },
    {
      "id": "matmul-gemm",
      "name": "GEMM / Tensor-Core matmul",
      "applies_to": [
        "nvidia-code-samples",
        "simveit-effective-transpose",
        "simveit-load-and-store",
        "colfax-article-src",
        "colfax-cutlass-kernels",
        "hygon-hip-kernel-optimizer",
        "rocm-aiter",
        "stackav-conch",
        "flaggems",
        "huggingface-kernels",
        "triton-distributed"
      ],
      "tags": [
        "gemm",
        "matmul",
        "tensor-core",
        "wgmma",
        "tma",
        "epilogue"
      ]
    },
    {
      "id": "moe",
      "name": "Mixture of Experts",
      "applies_to": [
        "simveit-effective-transpose",
        "simveit-load-and-store",
        "colfax-article-src",
        "colfax-cutlass-kernels",
        "hygon-hip-kernel-optimizer",
        "rocm-aiter",
        "huggingface-kernels",
        "triton-distributed"
      ],
      "tags": [
        "moe",
        "fused-moe",
        "grouped-gemm",
        "align-block-size",
        "top-k",
        "permute"
      ]
    },
    {
      "id": "normalization",
      "name": "RMSNorm / LayerNorm fused norms",
      "applies_to": [
        "nvidia-code-samples",
        "simveit-effective-transpose",
        "hygon-hip-kernel-optimizer",
        "rocm-aiter",
        "stackav-conch",
        "flaggems",
        "liger-kernel",
        "huggingface-kernels"
      ],
      "tags": [
        "rmsnorm",
        "layernorm",
        "fused-add-norm",
        "qk-norm",
        "qknorm"
      ]
    },
    {
      "id": "activation-fusion",
      "name": "Activation / element-wise fusion",
      "applies_to": [
        "simveit-effective-transpose",
        "hygon-hip-kernel-optimizer",
        "rocm-aiter",
        "stackav-conch",
        "flaggems",
        "liger-kernel",
        "huggingface-kernels"
      ],
      "tags": [
        "silu",
        "gelu",
        "swiglu",
        "fused-add",
        "fused-residual"
      ]
    },
    {
      "id": "quantization-fp8",
      "name": "FP8 / FP4 / INT8 quantization",
      "applies_to": [
        "simveit-effective-transpose",
        "simveit-load-and-store",
        "colfax-article-src",
        "colfax-cutlass-kernels",
        "hygon-hip-kernel-optimizer",
        "rocm-aiter",
        "stackav-conch",
        "flaggems",
        "huggingface-kernels"
      ],
      "tags": [
        "fp8",
        "fp4",
        "int8",
        "awq",
        "gptq",
        "block-scaled",
        "per-tensor",
        "per-channel"
      ]
    },
    {
      "id": "triton-open-kernel-libraries",
      "name": "Open Triton kernel libraries",
      "applies_to": [
        "rocm-aiter",
        "rocm-aotriton",
        "stackav-conch",
        "flaggems",
        "liger-kernel",
        "huggingface-kernels",
        "triton-distributed"
      ],
      "tags": [
        "triton",
        "open-source",
        "llm",
        "dcu",
        "rocm",
        "benchmark",
        "unit-test",
        "reference-implementation"
      ]
    },
    {
      "id": "distributed-triton",
      "name": "Distributed Triton and compute-communication overlap",
      "applies_to": [
        "rocm-aiter",
        "triton-distributed"
      ],
      "tags": [
        "triton",
        "distributed",
        "communication",
        "allreduce",
        "allgather",
        "reduce-scatter",
        "moe",
        "tensor-parallel",
        "expert-parallel"
      ]
    }
  ]
}