siboehm
commented
2 years ago This is exactly this issue: https://github.com/dmlc/treelite/issues/277
Minimally reproducible example:
```
tree
version=v3
num_class=1
num_tree_per_iteration=1
label_index=0
max_feature_idx=0
objective=regression
feature_names=Column_0
feature_infos=-1:0:1:2
tree_sizes=322
Tree=0
num_leaves=2
num_cat=1
split_feature=0
split_gain=500
threshold=0
decision_type=1
left_child=-1
right_child=-2
leaf_value=6.9999999920527145 6.5000000039736436
leaf_weight=30 60
leaf_count=30 60
internal_value=6.66667
internal_weight=0
internal_count=90
cat_boundaries=0 1
cat_threshold=1
is_linear=0
shrinkage=1
end of trees
feature_importances:
Column_0=1
parameters:
[boosting: gbdt]
[objective: regression]
[metric: l2]
[tree_learner: serial]
[device_type: cpu]
[data: ]
[valid: ]
[num_iterations: 1]
[learning_rate: 0.1]
[num_leaves: 31]
[num_threads: 0]
[deterministic: 0]
[force_col_wise: 0]
[force_row_wise: 0]
[histogram_pool_size: -1]
[max_depth: -1]
[min_data_in_leaf: 20]
[min_sum_hessian_in_leaf: 0.001]
[bagging_fraction: 1]
[pos_bagging_fraction: 1]
[neg_bagging_fraction: 1]
[bagging_freq: 0]
[bagging_seed: 3]
[feature_fraction: 1]
[feature_fraction_bynode: 1]
[feature_fraction_seed: 2]
[extra_trees: 0]
[extra_seed: 6]
[early_stopping_round: 0]
[first_metric_only: 0]
[max_delta_step: 0]
[lambda_l1: 0]
[lambda_l2: 0]
[linear_lambda: 0]
[min_gain_to_split: 0]
[drop_rate: 0.1]
[max_drop: 50]
[skip_drop: 0.5]
[xgboost_dart_mode: 0]
[uniform_drop: 0]
[drop_seed: 4]
[top_rate: 0.2]
[other_rate: 0.1]
[min_data_per_group: 100]
[max_cat_threshold: 32]
[cat_l2: 10]
[cat_smooth: 10]
[max_cat_to_onehot: 4]
[top_k: 20]
[monotone_constraints: ]
[monotone_constraints_method: basic]
[monotone_penalty: 0]
[feature_contri: ]
[forcedsplits_filename: ]
[refit_decay_rate: 0.9]
[cegb_tradeoff: 1]
[cegb_penalty_split: 0]
[cegb_penalty_feature_lazy: ]
[cegb_penalty_feature_coupled: ]
[path_smooth: 0]
[interaction_constraints: ]
[verbosity: 1]
[saved_feature_importance_type: 0]
[linear_tree: 0]
[max_bin: 255]
[max_bin_by_feature: ]
[min_data_in_bin: 3]
[bin_construct_sample_cnt: 200000]
[data_random_seed: 1]
[is_enable_sparse: 1]
[enable_bundle: 1]
[use_missing: 1]
[zero_as_missing: 0]
[feature_pre_filter: 1]
[pre_partition: 0]
[two_round: 0]
[header: 0]
[label_column: ]
[weight_column: ]
[group_column: ]
[ignore_column: ]
[categorical_feature: 0]
[forcedbins_filename: ]
[precise_float_parser: 0]
[objective_seed: 5]
[num_class: 1]
[is_unbalance: 0]
[scale_pos_weight: 1]
[sigmoid: 1]
[boost_from_average: 1]
[reg_sqrt: 0]
[alpha: 0.9]
[fair_c: 1]
[poisson_max_delta_step: 0.7]
[tweedie_variance_power: 1.5]
[lambdarank_truncation_level: 30]
[lambdarank_norm: 1]
[label_gain: ]
[eval_at: ]
[multi_error_top_k: 1]
[auc_mu_weights: ]
[num_machines: 1]
[local_listen_port: 12400]
[time_out: 120]
[machine_list_filename: ]
[machines: ]
[gpu_platform_id: -1]
[gpu_device_id: -1]
[gpu_use_dp: 0]
[num_gpu: 1]
end of parameters
pandas_categorical:null
```
import os
import lleaves
import lightgbm as lgb
import numpy.testing as npt
os.environ["LLEAVES_PRINT_UNOPTIMIZED_IR"] = "1"
os.environ["LLEAVES_PRINT_ASM"] = "1"
model_path = "faulty_model.txt"
llvm_model = lleaves.Model(model_file=model_path)
llvm_model.compile()
lgbm_model = lgb.Booster(model_file=model_path)
data = [[float("NaN")]]
npt.assert_equal(llvm_model.predict(data), lgbm_model.predict(data))lleaves returns 7.0, lightgbm returns 6.5
When running the (non-benchmark) test suite, 11 out of 90 tests are failing on an ARM M1 MBP, while the x86 CI continues running without errors. Seems to be related to fp NaN handling on ARM, haven't looked closely yet.