fix: reduce H100 replay buffer VRAM fraction 55% → 45% — OOM from IQN 8.6GB + Phase 2
IQN with 64 quantiles × batch=16384 allocates 8.6GB for tiled intermediates. Combined with attention (250MB), Phase 2 aux workspaces (64MB), backward branch scratch (16MB), the 55% replay fraction left only 349MB free — not enough for experience collector's 192MB next_states allocation. 45% frees ~8GB headroom: replay buffer 19.4M → ~15.9M (still 60× batch). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -4,7 +4,7 @@ batch_size = 16384
|
||||
num_atoms = 52
|
||||
buffer_size = 500000
|
||||
hidden_dim_base = 256
|
||||
replay_buffer_vram_fraction = 0.55 # state_dim=96, 86 weight tensors — leaves ~33GB for compute
|
||||
replay_buffer_vram_fraction = 0.45 # state_dim=96, 86 tensors + IQN 8.6GB + attention 250MB + Phase 2 128MB
|
||||
|
||||
[experience]
|
||||
gpu_timesteps_per_episode = 5000
|
||||
|
||||
Reference in New Issue
Block a user