# GLM-5-NVFP4 (nvidia/GLM-5-NVFP4) on 8 x B200 (192GB each).
# Architecture auto-loaded from HuggingFace config.json.
#
# FP4 weights: ~744B params * 0.5 bytes = ~372 GB across 8 GPUs.
# Total HBM: 8 * 192 GB = 1536 GB. Keep the KV budget below the raw
# remainder to leave room for runtime activations and allocator slack.

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: 8xb200
  hbm_bytes: 1150.0e9
  dram_bytes: 1.5e12
  max_batch_slots: 256

cluster:
  num_instances: 8
  meta_store:
    ttl_seconds: 300.0
  router:
    mode: prefix_affinity
    prefix_k: 8
    load_alpha: 1.0

sim:
  trace_path: bailian-traces/glm_coder_blksz_512_040915-040917.jsonl
  max_requests: null
  output_dir: runs/glm5_nvfp4_8xb200
  sample_interval_s: 1.0
  seed: 42