Gahow Wang
84696604e8
Add NVIDIA B300 (Blackwell Ultra) to hardware presets: same GB202 die as B200 (2.25 PFLOPS BF16 dense) but with HBM3e 12-Hi stacks (288 GB, 12 TB/s — 50% more capacity and bandwidth than B200). Add nvidia/GLM-5-NVFP4 HuggingFace config.json and a matching simulation config for 8xB300: FP4 weights (~372 GB) leave ~1.9 TB for KV cache, yielding 82k blocks per instance (3.8x more than the BF16-on-B200 setup). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
32 lines
826 B
YAML
32 lines
826 B
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
|
|
dtype_bytes: 1 # FP8 KV cache
|
|
block_size_tokens: 512
|
|
|
|
hardware:
|
|
type: 8xb300
|
|
hbm_bytes: 1900.0e9 # KV budget after FP4 weights (~372 GB)
|
|
|
|
cluster:
|
|
num_instances: 32
|
|
meta_store:
|
|
ttl_seconds: 120.0
|
|
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
|