e61e8f54da
Changes: - CLAUDE.md: Update OOM fix validation status - Add comprehensive documentation (30+ markdown reports) - LSTM encoder varmap bug fix (tft/lstm_encoder.rs:290) - Quantized LSTM layer matching fix (tft/quantized_lstm.rs) - Hyperopt paths module (ml/src/hyperopt/paths.rs) - Training path tests for all adapters (DQN, MAMBA-2, PPO, TFT) - Checkpoint integrity tests - Script cleanup: Remove 29 obsolete deployment scripts - Archive old scripts to scripts/archive/ - New deployment utilities: check_gpu_availability.py, monitor_hyperopt.sh Validation: - OOM fixes validated: 5/5 trials successful (pod b6kc3mc5lbjiro) - Batch-size-max 256 tested successfully - All hyperopt adapters working correctly 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
31 lines
969 B
Python
Executable File
31 lines
969 B
Python
Executable File
#!/usr/bin/env python3
|
|
import os
|
|
import sys
|
|
from pathlib import Path
|
|
from dotenv import load_dotenv
|
|
import runpod
|
|
|
|
# Load environment
|
|
env_path = Path.cwd().parent / '.env.runpod'
|
|
load_dotenv(env_path)
|
|
|
|
runpod.api_key = os.getenv('RUNPOD_API_KEY')
|
|
|
|
# Get GPU types and check specific GPUs
|
|
gpu_types = runpod.get_gpus()
|
|
target_gpus = ['RTX 4090', 'RTX 4000 Ada', 'RTX 5090']
|
|
|
|
for target in target_gpus:
|
|
for gpu in gpu_types:
|
|
if target in gpu.get('displayName', ''):
|
|
print(f"\n{target} details:")
|
|
print(f" secureCloud: {gpu.get('secureCloud', 0)}")
|
|
print(f" communityCloud: {gpu.get('communityCloud', 0)}")
|
|
print(f" memoryInGb: {gpu.get('memoryInGb', 0)}")
|
|
price_info = gpu.get('lowestPrice', {})
|
|
if price_info:
|
|
print(f" uninterruptablePrice: {price_info.get('uninterruptablePrice', 'N/A')}")
|
|
else:
|
|
print(f" price: N/A")
|
|
break
|