Files
aituner/runs/frontier-multicase-sufficiency-v0/results/community-qwen235b-smoke/profiles/compute/h20/moe_config.yaml

28 lines
594 B
YAML

block_shape: null
device: h20
disable_ray: true
disable_replicated: false
enable_load_imbalance: true
expert_parallel_sizes:
- 1
extra_num_tokens: null
gating_runtime_context: prefill_hot
load_distributions:
- uniform
max_tokens: 16
models:
- Qwen3-235B-A22B-FP8
num_gpus: 1
num_samples_per_distribution: 1
num_tensor_parallel_workers:
- 4
num_tokens_list:
- 16
output_dir: /home/admin/cpfs/wjh/frontier-community-qwen235-smoke-20260715/profiles
per_channel_quant: false
precision: null
profile_method: cuda_event
routing_runtime_path: standard_fused_topk
skip_confirmation: true
use_fp8: null