koko210Serve
1fc3d74a5b
Features: - Built custom ROCm container for AMD RX 6800 GPU - Added GPU selection toggle in web UI (NVIDIA/AMD) - Unified model names across both GPUs for seamless switching - Vision model always uses NVIDIA GPU (optimal performance) - Text models (llama3.1, darkidol) can use either GPU - Added /gpu-status and /gpu-select API endpoints - Implemented GPU state persistence in memory/gpu_state.json Technical details: - Multi-stage Dockerfile.llamaswap-rocm with ROCm 6.2.4 - llama.cpp compiled with GGML_HIP=ON for gfx1030 (RX 6800) - Proper GPU permissions without root (groups 187/989) - AMD container on port 8091, NVIDIA on port 8090 - Updated bot/utils/llm.py with get_current_gpu_url() and get_vision_gpu_url() - Modified bot/utils/image_handling.py to always use NVIDIA for vision - Enhanced web UI with GPU selector button (blue=NVIDIA, red=AMD) Files modified: - docker-compose.yml (added llama-swap-amd service) - bot/globals.py (added LLAMA_AMD_URL) - bot/api.py (added GPU selection endpoints and helper function) - bot/utils/llm.py (GPU routing for text models) - bot/utils/image_handling.py (GPU routing for vision models) - bot/static/index.html (GPU selector UI) - llama-swap-rocm-config.yaml (unified model names) New files: - Dockerfile.llamaswap-rocm - bot/memory/gpu_state.json - bot/utils/gpu_router.py (load balancing utility) - setup-dual-gpu.sh (setup verification script) - DUAL_GPU_*.md (documentation files)
99 lines
3.3 KiB
Python
99 lines
3.3 KiB
Python
# globals.py
|
|
import os
|
|
from collections import defaultdict, deque
|
|
import discord
|
|
from apscheduler.schedulers.asyncio import AsyncIOScheduler
|
|
|
|
scheduler = AsyncIOScheduler()
|
|
|
|
GUILD_SETTINGS = {}
|
|
|
|
# Stores last 5 exchanges per user (as deque)
|
|
conversation_history = defaultdict(lambda: deque(maxlen=5))
|
|
|
|
DISCORD_BOT_TOKEN = os.getenv("DISCORD_BOT_TOKEN")
|
|
|
|
# Autonomous V2 Debug Mode (set to True to see detailed decision logging)
|
|
AUTONOMOUS_DEBUG = os.getenv("AUTONOMOUS_DEBUG", "false").lower() == "true"
|
|
|
|
# Llama.cpp server settings (via llama-swap)
|
|
LLAMA_URL = os.getenv("LLAMA_URL", "http://llama-swap:8080")
|
|
LLAMA_AMD_URL = os.getenv("LLAMA_AMD_URL", "http://llama-swap-amd:8080") # Secondary AMD GPU
|
|
TEXT_MODEL = os.getenv("TEXT_MODEL", "llama3.1")
|
|
VISION_MODEL = os.getenv("VISION_MODEL", "vision")
|
|
EVIL_TEXT_MODEL = os.getenv("EVIL_TEXT_MODEL", "darkidol") # Uncensored model for evil mode
|
|
OWNER_USER_ID = int(os.getenv("OWNER_USER_ID", "209381657369772032")) # Bot owner's Discord user ID for reports
|
|
|
|
# Fish.audio TTS settings
|
|
FISH_API_KEY = os.getenv("FISH_API_KEY", "478d263d8c094e0c8993aae3e9cf9159")
|
|
MIKU_VOICE_ID = os.getenv("MIKU_VOICE_ID", "b28b79555e8c4904ac4d048c36e716b7")
|
|
|
|
# Set up Discord client
|
|
intents = discord.Intents.default()
|
|
intents.message_content = True
|
|
intents.members = True
|
|
intents.presences = True
|
|
client = discord.Client(intents=intents)
|
|
|
|
# Note: llama-swap handles model loading/unloading automatically
|
|
# No need to track current_model anymore
|
|
|
|
KINDNESS_KEYWORDS = [
|
|
"thank you", "love you", "luv u", "you're the best", "so cute",
|
|
"adorable", "amazing", "sweet", "kind", "great job", "well done",
|
|
"precious", "good girl", "cutie", "angel", "my favorite", "so helpful"
|
|
]
|
|
HEART_REACTIONS = ["💙", "💝", "💖", "💕", "💜", "❤️🔥", "☺️"]
|
|
kindness_reacted_messages = set()
|
|
|
|
# DM Mood System (simple, auto-rotating only)
|
|
DM_MOOD = "neutral"
|
|
DM_MOOD_DESCRIPTION = "I'm feeling neutral and balanced today."
|
|
AVAILABLE_MOODS = [
|
|
"bubbly", "sleepy", "curious", "shy", "serious", "excited", "silly",
|
|
"melancholy", "flirty", "romantic", "irritated", "angry", "neutral", "asleep"
|
|
]
|
|
|
|
# Evil Mode System
|
|
EVIL_MODE = False
|
|
EVIL_DM_MOOD = "evil_neutral"
|
|
EVIL_DM_MOOD_DESCRIPTION = "Evil Miku is calculating and cold."
|
|
EVIL_AVAILABLE_MOODS = ["aggressive", "cunning", "sarcastic", "evil_neutral"]
|
|
EVIL_MOOD_EMOJIS = {
|
|
"aggressive": "👿",
|
|
"cunning": "🐍",
|
|
"sarcastic": "😈",
|
|
"evil_neutral": ""
|
|
}
|
|
|
|
# Bipolar Mode System (both Mikus can argue via webhooks)
|
|
BIPOLAR_MODE = False
|
|
BIPOLAR_WEBHOOKS = {} # guild_id -> {"miku_webhook_url": str, "evil_webhook_url": str}
|
|
BIPOLAR_ARGUMENT_IN_PROGRESS = {} # channel_id -> {"active": bool, "exchange_count": int, "current_speaker": str}
|
|
|
|
# Regular Miku mood emojis (used in bipolar mode for webhook display names)
|
|
MOOD_EMOJIS = {
|
|
"bubbly": "✨",
|
|
"sleepy": "💤",
|
|
"curious": "🔍",
|
|
"shy": "🥺",
|
|
"serious": "😐",
|
|
"excited": "🎉",
|
|
"silly": "🤪",
|
|
"melancholy": "💙",
|
|
"flirty": "💕",
|
|
"romantic": "💖",
|
|
"irritated": "😤",
|
|
"angry": "😠",
|
|
"neutral": "",
|
|
"asleep": "😴"
|
|
}
|
|
|
|
BOT_USER = None
|
|
|
|
LAST_FULL_PROMPT = ""
|
|
|
|
# Persona Dialogue System (conversations between Miku and Evil Miku)
|
|
LAST_PERSONA_DIALOGUE_TIME = 0 # Timestamp of last dialogue for cooldown
|
|
|