35 lines
1.0 KiB
YAML
35 lines
1.0 KiB
YAML
# GLM-5-NVFP4 (nvidia/GLM-5-NVFP4) on 8 x B300 (Blackwell Ultra, 288GB each).
|
|
# Architecture auto-loaded from HuggingFace config.json.
|
|
#
|
|
# FP4 weights: ~744B params * 0.5 bytes = ~372 GB across 8 GPUs.
|
|
# Total HBM: 8 * 288 GB = 2304 GB. KV budget: ~1900 GB after weights.
|
|
|
|
model:
|
|
config_json: ../models/GLM-5-NVFP4/config.json
|
|
name: glm-5-nvfp4
|
|
compute_dtype: fp8 # FP8 tensor-core execution
|
|
weight_dtype: fp4 # NVFP4 weights still set the HBM budget
|
|
dtype_bytes: 1 # FP8 KV cache
|
|
block_size_tokens: 512
|
|
|
|
hardware:
|
|
type: 8xb300
|
|
hbm_bytes: 1900.0e9 # KV budget after FP4 weights (~372 GB)
|
|
dram_bytes: 1.5e12 # ~1.5 TB usable CPU DRAM per node
|
|
|
|
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_8xb300
|
|
sample_interval_s: 1.0
|
|
seed: 42
|