{
  "op": "com.microsoft.PagedAttention",
  "tunableSpace": {
    "WORKGROUP_SIZE": [32, 64, 128],
    "SCATTER_WORKGROUP_SIZE": [64, 128, 256],
    "SPLIT_TARGET_WORKGROUPS": [512, 1024, 2048, 4096],
    "SPLIT_MIN_KEYS": [64, 128, 256],
    "MAX_SPLITS": [8, 16, 32]
  },
  "cases": [
    {
      "name": "paged-decode-b8-past1024-h32kv8-d128",
      "preset": "smoke",
      "vars": { "dtype": "float16", "batch": 8, "past": 1024, "heads": 32, "kvHeads": 8, "headDim": 128 },
      "attrs": { "num_heads": 32, "kv_num_heads": 8 },
      "inputs": {
        "queryT": { "shape": [8, 4096], "dtype": "float16", "dist": "normal", "seed": 9201, "scale": 1 },
        "keyT": { "shape": [8, 1024], "dtype": "float16", "dist": "normal", "seed": 9202, "scale": 1 },
        "valueT": { "shape": [8, 1024], "dtype": "float16", "dist": "normal", "seed": 9203, "scale": 1 },
        "keyCacheT": { "shape": [512, 16, 8, 128], "dtype": "float16", "dist": "normal", "seed": 9204, "scale": 1 },
        "valueCacheT": { "shape": [512, 16, 8, 128], "dtype": "float16", "dist": "normal", "seed": 9205, "scale": 1 },
        "cumulativeSequenceLengthT": {
          "shape": [9],
          "dtype": "int32",
          "data": { "kind": "values", "values": [0, 1, 2, 3, 4, 5, 6, 7, 8] }
        },
        "pastSeqlensT": { "shape": [8], "dtype": "int32", "dist": "constant", "value": 1023 },
        "blockTableT": { "shape": [8, 64], "dtype": "int32", "dist": "linearMod", "seed": 9208, "step": 1, "mod": 512 }
      },
      "outputs": { "outputT": { "shape": [8, 4096], "dtype": "float16" } },
      "bench": {
        "metrics": [{ "type": "bandwidth", "value": "2 * args.batch * args.kvHeads * args.past * args.headDim * 2" }]
      },
      "provenance": {
        "notes": "The KV bytes are counted off named vars like the model cases, not hardcoded: the literal this replaced used the QUERY head count for a grouped-query shape and four bytes for a float16 cache, so it over-stated the traffic eightfold and the case reported an impossible rate."
      }
    },
    {
      "name": "paged-decode-llama-b16-past2048-h32kv32-d128",
      "preset": "model",
      "provenance": {
        "notes": "Llama class defaults (32 query heads, no GQA, head_dim 128) decoding 16 concurrent sequences with 2048 tokens of paged KV each."
      },
      "vars": { "dtype": "float16", "batch": 16, "past": 2048, "heads": 32, "kvHeads": 32, "headDim": 128 },
      "attrs": { "num_heads": 32, "kv_num_heads": 32 },
      "inputs": {
        "queryT": { "shape": [16, 4096], "dtype": "float16", "dist": "normal", "seed": 7600, "scale": 0.3 },
        "keyT": { "shape": [16, 4096], "dtype": "float16", "dist": "normal", "seed": 7601, "scale": 0.3 },
        "valueT": { "shape": [16, 4096], "dtype": "float16", "dist": "normal", "seed": 7602, "scale": 0.3 },
        "keyCacheT": { "shape": [2048, 16, 32, 128], "dtype": "float16", "dist": "normal", "seed": 7603, "scale": 0.3 },
        "valueCacheT": {
          "shape": [2048, 16, 32, 128],
          "dtype": "float16",
          "dist": "normal",
          "seed": 7604,
          "scale": 0.3
        },
        "cumulativeSequenceLengthT": {
          "shape": [17],
          "dtype": "int32",
          "dist": "linearMod",
          "seed": 7605,
          "step": 1,
          "mod": 17
        },
        "pastSeqlensT": { "shape": [16], "dtype": "int32", "dist": "constant", "value": 2048 },
        "blockTableT": {
          "shape": [16, 128],
          "dtype": "int32",
          "dist": "linearMod",
          "seed": 7606,
          "step": 1,
          "mod": 2048
        }
      },
      "outputs": { "outputT": { "shape": [16, 4096], "dtype": "float16" } },
      "bench": {
        "metrics": [{ "type": "bandwidth", "value": "2 * args.batch * args.kvHeads * args.past * args.headDim * 2" }]
      }
    },
    {
      "name": "paged-decode-mistral-b16-past4096-h32kv8-d128",
      "preset": "model",
      "provenance": {
        "notes": "Mistral class defaults (32 query heads, 8 key/value heads, head_dim 128) at 4096 tokens of history -- the GQA case, where the cache is a quarter the size for the same context."
      },
      "vars": { "dtype": "float16", "batch": 16, "past": 4096, "heads": 32, "kvHeads": 8, "headDim": 128 },
      "attrs": { "num_heads": 32, "kv_num_heads": 8 },
      "inputs": {
        "queryT": { "shape": [16, 4096], "dtype": "float16", "dist": "normal", "seed": 7700, "scale": 0.3 },
        "keyT": { "shape": [16, 1024], "dtype": "float16", "dist": "normal", "seed": 7701, "scale": 0.3 },
        "valueT": { "shape": [16, 1024], "dtype": "float16", "dist": "normal", "seed": 7702, "scale": 0.3 },
        "keyCacheT": { "shape": [4096, 16, 8, 128], "dtype": "float16", "dist": "normal", "seed": 7703, "scale": 0.3 },
        "valueCacheT": { "shape": [4096, 16, 8, 128], "dtype": "float16", "dist": "normal", "seed": 7704, "scale": 0.3 },
        "cumulativeSequenceLengthT": {
          "shape": [17],
          "dtype": "int32",
          "dist": "linearMod",
          "seed": 7705,
          "step": 1,
          "mod": 17
        },
        "pastSeqlensT": { "shape": [16], "dtype": "int32", "dist": "constant", "value": 4096 },
        "blockTableT": {
          "shape": [16, 256],
          "dtype": "int32",
          "dist": "linearMod",
          "seed": 7706,
          "step": 1,
          "mod": 4096
        }
      },
      "outputs": { "outputT": { "shape": [16, 4096], "dtype": "float16" } },
      "bench": {
        "metrics": [{ "type": "bandwidth", "value": "2 * args.batch * args.kvHeads * args.past * args.headDim * 2" }]
      }
    },
    {
      "name": "paged-decode-gemma3-b8-past2048-h8kv4-d256",
      "preset": "model",
      "provenance": {
        "notes": "Gemma3 class defaults (8 query heads, 4 key/value heads, head_dim 256) -- few heads but the widest head dimension in this set."
      },
      "vars": { "dtype": "float16", "batch": 8, "past": 2048, "heads": 8, "kvHeads": 4, "headDim": 256 },
      "attrs": { "num_heads": 8, "kv_num_heads": 4 },
      "inputs": {
        "queryT": { "shape": [8, 2048], "dtype": "float16", "dist": "normal", "seed": 7800, "scale": 0.3 },
        "keyT": { "shape": [8, 1024], "dtype": "float16", "dist": "normal", "seed": 7801, "scale": 0.3 },
        "valueT": { "shape": [8, 1024], "dtype": "float16", "dist": "normal", "seed": 7802, "scale": 0.3 },
        "keyCacheT": { "shape": [1024, 16, 4, 256], "dtype": "float16", "dist": "normal", "seed": 7803, "scale": 0.3 },
        "valueCacheT": { "shape": [1024, 16, 4, 256], "dtype": "float16", "dist": "normal", "seed": 7804, "scale": 0.3 },
        "cumulativeSequenceLengthT": {
          "shape": [9],
          "dtype": "int32",
          "dist": "linearMod",
          "seed": 7805,
          "step": 1,
          "mod": 9
        },
        "pastSeqlensT": { "shape": [8], "dtype": "int32", "dist": "constant", "value": 2048 },
        "blockTableT": {
          "shape": [8, 128],
          "dtype": "int32",
          "dist": "linearMod",
          "seed": 7806,
          "step": 1,
          "mod": 1024
        }
      },
      "outputs": { "outputT": { "shape": [8, 2048], "dtype": "float16" } },
      "bench": {
        "metrics": [{ "type": "bandwidth", "value": "2 * args.batch * args.kvHeads * args.past * args.headDim * 2" }]
      }
    }
  ]
}