# MLA decode-only benchmark configuration

model:
  name: "deepseek-v3"
  num_layers: 60
  num_q_heads: 128  # Base value, can be swept for TP simulation
  num_kv_heads: 1  # MLA uses single latent KV
  head_dim: 576
  kv_lora_rank: 512
  qk_nope_head_dim: 128
  qk_rope_head_dim: 64
  v_head_dim: 128
  block_size: 128  # CUTLASS MLA and FlashAttn MLA use 128

# Model parameter sweep: simulate tensor parallelism by varying num_q_heads
# TP=1: 128 heads, TP=2: 64 heads, TP=4: 32 heads, TP=8: 16 heads
model_parameter_sweep:
  param_name: "num_q_heads"
  values: [128, 64, 32, 16]
  label_format: "{backend}_{value}h"

batch_specs:
  # Small batches, varying sequence lengths
  - "16q1s512"     # 16 requests, 512 KV cache
  - "16q1s1k"      # 16 requests, 1k KV cache
  - "16q1s2k"      # 16 requests, 2k KV cache
  - "16q1s4k"      # 16 requests, 4k KV cache

  # Medium batches
  - "32q1s1k"      # 32 requests, 1k KV cache
  - "32q1s2k"      # 32 requests, 2k KV cache
  - "32q1s4k"      # 32 requests, 4k KV cache
  - "32q1s8k"      # 32 requests, 8k KV cache

  # Large batches
  - "64q1s1k"      # 64 requests, 1k KV cache
  - "64q1s2k"      # 64 requests, 2k KV cache
  - "64q1s4k"      # 64 requests, 4k KV cache
  - "64q1s8k"      # 64 requests, 8k KV cache

  # Very large batches
  - "128q1s1k"     # 128 requests, 1k KV cache
  - "128q1s2k"     # 128 requests, 2k KV cache
  - "128q1s4k"     # 128 requests, 4k KV cache
  - "128q1s8k"     # 128 requests, 8k KV cache

  # Long context
  - "32q1s16k"     # 32 requests, 16k KV cache
  - "32q1s32k"     # 32 requests, 32k KV cache

backends:
  - FLASHMLA_SPARSE
  - FLASHINFER_MLA_SPARSE

device: "cuda:0"
repeats: 100
warmup_iters: 10
profile_memory: true