# GLM-5-FP8 (ZhipuAI/GLM-5-FP8) on 8 x H20-141G (N3E).
# Tuned for the 0-32768 input-length slice of
# bailian-traces/glm_coder_blksz_512_040915-040917.jsonl.

model:
  config_json: ../models/GLM-5-FP8/config.json
  name: glm-5-fp8
  compute_dtype: fp8
  dtype_bytes: 1
  block_size_tokens: 512

hardware:
  type: 8xh20-141g
  hbm_bytes: 300.0e9
  dram_bytes: 1.5e12
  max_batch_slots: 256

cluster:
  num_instances: 64
  meta_store:
    ttl_seconds: 300.0
  router:
    mode: cache_affinity
    precise_probe_latency_us: 50.0
    precise_probe_topk: 4
    # Tuned on this filtered GLM coder workload: stronger queue penalty than
    # the default 1.0 keeps cache_affinity's locality gains while reducing TTFT.
    load_alpha: 1.5
    prefix_k: 8

sim:
  trace_path: bailian-traces/glm_coder_blksz_512_040915-040917.jsonl
  max_requests: null
  output_dir: runs/glm5_fp8_8xh20_141g_ca_tuned
  sample_interval_s: 1.0
  seed: 42
  input_length_min: 0
  input_length_max: 32768