e4b7d2ffb0
Created config/gpu/{default,rtx3050,h100,a100}.toml with all GPU-specific
parameters: batch_size, num_atoms, buffer_size, hidden_dim_base,
replay_buffer_vram_fraction, gpu_n_episodes, gpu_timesteps_per_episode,
cuda_stack_bytes.
GpuProfile::load() auto-detects GPU by device name, falls back to
embedded defaults (include_str!). Override via FOXHUNT_GPU_PROFILE env.
Removed dead code:
- detect_vram_mb(), vram_scaled_hidden_dims(), vram_scaled_base_dim(),
resolve_hidden_dim_base() + 18 tests for these functions
All callers updated: train_baseline_rl, DQNTrainer constructor,
PPO trainer, smoke tests, pipeline tests.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
15 lines
292 B
TOML
15 lines
292 B
TOML
# Default GPU profile -- conservative settings for unknown GPUs
|
|
[training]
|
|
batch_size = 256
|
|
num_atoms = 21
|
|
buffer_size = 50_000
|
|
hidden_dim_base = 256
|
|
replay_buffer_vram_fraction = 0.50
|
|
|
|
[experience]
|
|
gpu_n_episodes = 64
|
|
gpu_timesteps_per_episode = 200
|
|
|
|
[cuda]
|
|
cuda_stack_bytes = 32768 # 32KB
|