# H100 PCIe/SXM (80GB VRAM) -- full production
[training]
batch_size = 1024
num_atoms = 51
buffer_size = 500_000
hidden_dim_base = 256
replay_buffer_vram_fraction = 0.70

[experience]
# 2048 episodes: cuBLAS SGEMM batch=2048 saturates 132 SMs.
# At 256 episodes, the tiny 256×48 GEMMs leave >90% of SMs idle.
# 2048×100 = 204K experiences/epoch (vs 256×500 = 128K).
gpu_n_episodes = 2048
gpu_timesteps_per_episode = 100

[cuda]
cuda_stack_bytes = 65536  # 64KB