From: Jérôme Benoit Date: Sun, 15 Feb 2026 15:09:31 +0000 (+0100) Subject: docs(quickadapter): clarify gpu_vram_gb is available VRAM, not total X-Git-Url: https://git.piment-noir.org/?a=commitdiff_plain;h=1659c7bfcfbd5492dae995846d1ed90e248fbd87;p=freqai-strategies.git docs(quickadapter): clarify gpu_vram_gb is available VRAM, not total --- diff --git a/README.md b/README.md index c4e8e79..1a374ab 100644 --- a/README.md +++ b/README.md @@ -60,7 +60,7 @@ docker compose up -d --build | _Regressor model_ | | | | | freqai.regressor | `xgboost` | enum {`xgboost`,`lightgbm`,`histgradientboostingregressor`,`ngboost`,`catboost`} | Machine learning regressor algorithm. | | _Model training parameters_ | | | | -| freqai.model_training_parameters.gpu_vram_gb | 80 | enum {8,10,12,16,24,32,40,48,64,80} | GPU VRAM capacity (GB) for CatBoost. Constrains `depth`, `border_count`, and `max_ctr_complexity` ranges to fit memory. | +| freqai.model_training_parameters.gpu_vram_gb | 80 | enum {8,10,12,16,24,32,40,48,64,80} | Available GPU VRAM (GB) for CatBoost, not total. Constrains `depth`, `border_count`, and `max_ctr_complexity` ranges. | | _Data split parameters_ | | | | | freqai.data_split_parameters.method | `train_test_split` | enum {`train_test_split`,`timeseries_split`} | Data splitting strategy. `train_test_split` for sequential split, `timeseries_split` for chronological split with configurable gap. | | freqai.data_split_parameters.test_size | 0.1 / None | float (0,1) \| int >= 1 \| None | Test set size. Float for fraction, int for count. Default: 0.1 for `train_test_split`, None for `timeseries_split` (sklearn dynamic sizing). | diff --git a/quickadapter/user_data/strategies/Utils.py b/quickadapter/user_data/strategies/Utils.py index 598cda3..128d974 100644 --- a/quickadapter/user_data/strategies/Utils.py +++ b/quickadapter/user_data/strategies/Utils.py @@ -2129,7 +2129,7 @@ _CATBOOST_GPU_PAIRWISE_LOSS_FUNCTIONS: Final[tuple[str, ...]] = ( "QueryCrossEntropy", ) -# CatBoost GPU param ranges keyed by VRAM capacity (GB). +# CatBoost GPU param ranges keyed by available VRAM (GB), not total. # Formula: VRAM_MB = 58778 * 2^(depth-12) * (border_count+1) / 256 _CATBOOST_GPU_VRAM_PARAM_RANGES: Final[dict[int, dict[str, tuple[int, int]]]] = { 8: {"depth": (4, 9), "border_count": (32, 192), "max_ctr_complexity": (1, 4)},