# GLM-5 using HuggingFace config.json + hardware preset.
#
# This config demonstrates the simplified format:
#   model.config_json  — loads architecture from HF config.json
#   hardware.type      — loads GPU specs from built-in preset
#
# Only deployment-specific fields need to be set explicitly.
# Any field from config_json or the preset can be overridden in YAML.

model:
  # Auto-detect architecture: MoE, MLA, DSA, head dims, etc.
  config_json: ../models/GLM-5/config.json
  name: glm-5                    # override HF model_type
  dtype_bytes: 1                 # BF16 (not in HF config.json)
  block_size_tokens: 512         # matches bailian-traces blksz_512

hardware:
  type: 8xb200                   # 8 x B200 SXM (192GB each)
  # Override preset values for this specific deployment:
  hbm_bytes: 500.0e9             # KV budget after FP8 weights + activations
  dram_bytes: 1.5e12             # ~1.5 TB usable CPU DRAM per node
  max_batch_slots: 256

cluster:
  num_instances: 32
  meta_store:
    ttl_seconds: 300.0
  router:
    mode: min_pd
    precise_probe_latency_us: 50.0
    precise_probe_topk: 4
    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_8xb200_hf
  sample_interval_s: 1.0
  seed: 42