# Qwen2.5-Coder-7B using hardware preset.
#
# Model architecture is specified inline (no config.json needed for simple
# models). Hardware uses preset "h800" with a single override for hbm_bytes.

model:
  name: qwen2.5-coder-7b
  num_layers: 28
  hidden_size: 3584
  num_attention_heads: 28
  num_kv_heads: 4
  head_dim: 128
  intermediate_size: 18944
  dtype_bytes: 2
  block_size_tokens: 16

hardware:
  type: h800                     # single H800 SXM (80GB)
  hbm_bytes: 60.0e9             # KV budget after 7B model weights

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: qwen-bailian-usagetraces-anon/qwen_coder_blksz_16.jsonl
  max_requests: null
  output_dir: runs/qwen7b_preset
  sample_interval_s: 1.0
  seed: 42