f5b21406a8
Auto-scaling returned 8192 on 4GB RTX 3050 (should be 64), causing 17s/epoch instead of 0.28s. The VRAM math didn't account for IQN (1.1GB), attention, IQL, replay buffer (70% VRAM). Profile-tested values: - RTX 3050: 64 (4GB, minimal) - A100: 2048 (40-80GB) - H100: 8192 (80GB, production) - Default: 256 (conservative) Auto-scaling remains as fallback for batch_size=0 (unknown GPU). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
14 lines
289 B
TOML
14 lines
289 B
TOML
# Default GPU profile -- conservative settings for unknown GPUs
|
|
[training]
|
|
batch_size = 256
|
|
num_atoms = 21
|
|
buffer_size = 0 # 0 = auto from VRAM
|
|
hidden_dim_base = 256
|
|
replay_buffer_vram_fraction = 0.50
|
|
|
|
[experience]
|
|
gpu_timesteps_per_episode = 200
|
|
|
|
[cuda]
|
|
cuda_stack_bytes = 32768 # 32KB
|