# GLM-5-NVFP4 on 8 x B300 for the 128k++ bucket.
# A single instance already keeps mean TTFT below 5s, and routing is
# effectively irrelevant at N=1 because every request lands on the same node.

model:
  config_json: ../models/GLM-5-NVFP4/config.json
  name: glm-5-nvfp4
  compute_dtype: fp8
  weight_dtype: fp4
  dtype_bytes: 1
  block_size_tokens: 512

hardware:
  type: 8xb300
  hbm_bytes: 1900.0e9
  dram_bytes: 1.5e12
  max_batch_slots: 256

cluster:
  num_instances: 1
  meta_store:
    ttl_seconds: 300.0
  router:
    mode: cache_affinity
    precise_probe_latency_us: 50.0
    precise_probe_topk: 1
    load_alpha: 1.0
    prefix_k: 8

sim:
  trace_path: bailian-traces/glm_coder_blksz_512_040915-040917.jsonl
  max_requests: null
  output_dir: runs/glm5_nvfp4_8xb300_ablation_131073_plus_n1
  sample_interval_s: 1.0
  seed: 42
  input_length_min: 131073
  input_length_max: 4294967295