mirror of
https://github.com/mindverse/Second-Me.git
synced 2026-07-18 05:33:26 +00:00
053090937d
* Add CUDA support - CUDA detection - Memory handling - Ollama model release after training * Fix logging issue added cuda support flag so log accurately reflected cuda toggle * Update llama.cpp rebuild Changed llama.cpp to only check if cuda support is enabled and if so rebuild during the first build rather than each run * Improved vram management Enabled memory pinning and optimizer state offload * Fix CUDA check rewrote llama.cpp rebuild logic, added manual y/n toggle if user wants to enable cuda support * Added fast restart and fixed CUDA check command Added make docker-restart-backend-fast to restart the backend and reflect code changes without causing a full llama.cpp rebuild Fixed make docker-check-cuda command to correctly reflect cuda support * Added docker-compose.gpu.yml Added docker-compose.gpu.yml to fix error on machines without nvidia gpu and made sure "\n" is added before .env modification * Fixed cuda toggle Last push accidentally broke cuda toggle * Code review fixes Fixed errors resulting from removed code: - Added return save_path to end of save_hf_model function - Rolled back download_file_with_progress function * Update Makefile Use cuda by default when using docker-restart-backend-fast * Minor cleanup Removed unnecessary makefile command and fixed gpu logging * Delete .gpu_selected * Simplified cuda training code - Removed dtype setting to let torch automatically handle it - Removed vram logging - Removed Unnecessary/old comments * Fixed gpu/cpu selection Made "make docker-use-gpu/cpu" command work with .gpu_selected flag and changed "make docker-restart-backend-fast" command to respect flag instead of always using gpu * Fix Ollama embedding error Added custom exception class for Ollama embeddings, which seemed to be returning keyword arguments while the Python exception class only accepts positional ones * Fixed model selection & memory error Fixed training defaulting to 0.5B model regardless of selection and fixed "free(): double free detected in tcache 2" error caused by cuda flag being passed incorrectly
52 lines
No EOL
1.8 KiB
Python
52 lines
No EOL
1.8 KiB
Python
#!/usr/bin/env python3
|
|
|
|
import torch
|
|
import subprocess
|
|
import sys
|
|
import os
|
|
|
|
print("=== PyTorch CUDA Version Information ===")
|
|
print(f"PyTorch version: {torch.__version__}")
|
|
|
|
if torch.cuda.is_available():
|
|
print(f"CUDA available: Yes")
|
|
print(f"CUDA version used by PyTorch: {torch.version.cuda}")
|
|
print(f"cuDNN version: {torch.backends.cudnn.version() if torch.backends.cudnn.is_available() else 'Not available'}")
|
|
print(f"GPU device name: {torch.cuda.get_device_name(0)}")
|
|
|
|
# Try to check system CUDA version
|
|
try:
|
|
nvcc_output = subprocess.check_output(["nvcc", "--version"]).decode("utf-8")
|
|
print("\nSystem NVCC version:")
|
|
print(nvcc_output)
|
|
except:
|
|
print("\nNVCC not found in PATH")
|
|
|
|
# Check CUDA libraries
|
|
try:
|
|
print("\nChecking required CUDA libraries:")
|
|
for lib in ["libcudart.so", "libcublas.so", "libcublasLt.so"]:
|
|
print(f"\nSearching for {lib}:")
|
|
find_result = subprocess.run(f"find /usr -name '{lib}*'", shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
|
if find_result.returncode == 0 and find_result.stdout:
|
|
print(find_result.stdout.decode("utf-8"))
|
|
else:
|
|
print(f"No {lib} found in /usr")
|
|
except Exception as e:
|
|
print(f"Error checking libraries: {e}")
|
|
|
|
# Check LD_LIBRARY_PATH
|
|
print("\nLD_LIBRARY_PATH:")
|
|
print(os.environ.get("LD_LIBRARY_PATH", "Not set"))
|
|
|
|
else:
|
|
print("CUDA not available")
|
|
|
|
# Check system CUDA installation
|
|
print("\n=== System CUDA Information ===")
|
|
try:
|
|
nvidia_smi = subprocess.check_output(["nvidia-smi"]).decode("utf-8")
|
|
print("NVIDIA-SMI output:")
|
|
print(nvidia_smi)
|
|
except:
|
|
print("nvidia-smi not found or not working") |