# Qwen2.5-Coder-32B (dense, GQA) on H800 SXM (80GB).
# Architecture from HuggingFace config.json — roofline auto-derived.

model:
  name: qwen2.5-coder-32b
  num_layers: 64
  hidden_size: 5120
  num_attention_heads: 40
  num_kv_heads: 8              # GQA
  head_dim: 128
  intermediate_size: 27648     # SwiGLU FFN
  dtype_bytes: 2               # BF16
  block_size_tokens: 16

hardware:
  gpu_flops:        9.89e14
  gpu_mem_bw:       3.35e12
  hbm_bytes:        20.0e9     # smaller budget: 32B weights are large
  dram_bytes:       512.0e9
  pcie_bw:          64.0e9
  pcie_latency_us:  5.0
  rdma_bw:          25.0e9
  rdma_latency_us:  8.0
  max_batch_slots:  128
  prefill_chunk_tokens: 1024

cluster:
  num_instances: 16
  meta_store:
    ttl_seconds: 60.0
  router:
    mode: ttl_aware
    precise_probe_latency_us: 50.0
    precise_probe_topk: 4
    load_alpha: 1.0

sim:
  trace_path: traces/qwen_coder_blksz_16.jsonl
  max_requests: null
  output_dir: runs/qwen32b
  sample_interval_s: 1.0
  seed: 42