Files
kvcache-simulator/configs/glm5-nvfp4-8xb200-32k-85k-n5.yaml

37 lines
800 B
YAML

# GLM-5-NVFP4 on 8 x B200 for the 32k-85k bucket.
# Chosen to keep the best policy's mean TTFT below 5s.
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: 5
meta_store:
ttl_seconds: 300.0
router:
mode: cache_affinity
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_nvfp4_8xb200_ablation_32769_87040_n5
sample_interval_s: 1.0
seed: 42
input_length_min: 32769
input_length_max: 87040