Spaces:
Sleeping
Sleeping
File size: 9,847 Bytes
234574a | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 | """VRAM-pressure-aware eviction cache - IMPROVEMENT-002.
Replaces static TTL-based eviction with adaptive LRU/LFU hybrid that responds
to actual GPU memory pressure. Monitors MI300X VRAM via PyRSMI and adjusts
eviction policy dynamically.
Eviction modes:
- RELAXED (VRAM < 70%): No eviction, TTL = 10 minutes
- NORMAL (70-85%): LRU eviction of entries idle > 2 min
- PRESSURE (85-92%): LFU by token_count, evict heaviest first
- CRITICAL (92-96%): Offload inactive KV tensors to CPU RAM
- EMERGENCY (VRAM >= 96%): Hard evict all idle > 30s, block new registrations
"""
import asyncio
import heapq
import time
from dataclasses import dataclass, field
from enum import Enum
from typing import Any, Optional
from contextforge.metrics.vram_monitor import VRAMMonitor
class EvictionMode(Enum):
RELAXED = "relaxed"
NORMAL = "normal"
PRESSURE = "pressure"
CRITICAL = "critical"
EMERGENCY = "emergency"
@dataclass(order=True)
class CacheEntry:
# Priority for heap (lower = evict first): last_accessed - (access_count * 10)
# LFU/LRU hybrid: frequent+recent entries survive longer
priority: float = field(compare=True)
last_accessed: float = field(compare=False, default_factory=time.monotonic)
access_count: int = field(compare=False, default=0)
token_count: int = field(compare=False, default=0)
key: str = field(compare=False, default="")
value: Any = field(compare=False, default=None)
offloaded_to_cpu: bool = field(compare=False, default=False)
class VRAMAwareCache:
"""
LRU/LFU hybrid cache with VRAM pressure-responsive eviction.
Monitors AMD MI300X memory in real-time via PyRSMI.
Usage:
cache = VRAMAwareCache(max_token_budget=50_000_000) # 50M tokens = ~3GB
await cache.start()
await cache.set("agent1", context_entry, token_count=500)
entry = await cache.get("agent1")
await cache.stop()
"""
VRAM_CHECK_INTERVAL = 2.0 # seconds between VRAM pressure checks
def __init__(self, max_token_budget: int = 50_000_000):
"""
Args:
max_token_budget: Maximum tokens to hold in cache (~3GB for 64-layer model)
"""
self._store: dict[str, CacheEntry] = {}
self._heap: list[CacheEntry] = []
self._total_tokens: int = 0
self._max_token_budget = max_token_budget
self._vram = VRAMMonitor()
self._mode = EvictionMode.RELAXED
self._lock = asyncio.Lock()
self._monitor_task: Optional[asyncio.Task] = None
self._blocked = False
async def start(self) -> None:
"""Start background VRAM monitor."""
if self._monitor_task is not None:
return
self._monitor_task = asyncio.create_task(self._vram_monitor_loop())
async def stop(self) -> None:
"""Stop background monitoring."""
if self._monitor_task:
self._monitor_task.cancel()
try:
await self._monitor_task
except asyncio.CancelledError:
pass
self._monitor_task = None
async def _vram_monitor_loop(self) -> None:
"""Background loop: check VRAM pressure every interval."""
while True:
try:
pressure = self._vram.get_pressure()
new_mode = self._pressure_to_mode(pressure)
if new_mode != self._mode:
self._mode = new_mode
if new_mode == EvictionMode.EMERGENCY:
self._blocked = True
elif self._mode == EvictionMode.EMERGENCY:
self._blocked = False
await self._apply_eviction_policy()
await asyncio.sleep(self.VRAM_CHECK_INTERVAL)
except asyncio.CancelledError:
break
except Exception as e:
await asyncio.sleep(1) # Brief backoff on error
@staticmethod
def _pressure_to_mode(pressure: float) -> EvictionMode:
"""Convert VRAM pressure to eviction mode."""
if pressure < 0.70: return EvictionMode.RELAXED
if pressure < 0.85: return EvictionMode.NORMAL
if pressure < 0.92: return EvictionMode.PRESSURE
if pressure < 0.96: return EvictionMode.CRITICAL
return EvictionMode.EMERGENCY
async def set(self, key: str, value: Any, token_count: int) -> bool:
"""
Store value in cache.
Args:
key: Cache key (e.g., "context:agent1")
value: Value to store
token_count: Token count for VRAM tracking
Returns:
True if stored, False if blocked in EMERGENCY mode
"""
if self._blocked:
return False
entry = CacheEntry(
priority=time.monotonic(), # Will be updated by LRU/LFU formula
last_accessed=time.monotonic(),
access_count=1,
token_count=token_count,
key=key,
value=value,
)
async with self._lock:
# Evict old entry if key exists
if key in self._store:
old_entry = self._store[key]
self._total_tokens -= old_entry.token_count
self._store[key] = entry
heapq.heappush(self._heap, entry)
self._total_tokens += token_count
# Trigger eviction check if needed
if self._mode in (EvictionMode.PRESSURE, EvictionMode.CRITICAL, EvictionMode.EMERGENCY):
await self._apply_eviction_policy()
return True
async def get(self, key: str) -> Any | None:
"""Retrieve value, updating access metadata."""
async with self._lock:
entry = self._store.get(key)
if entry is None:
return None
# Update access metadata
entry.last_accessed = time.monotonic()
entry.access_count += 1
# Recalculate priority: lower = evict first
entry.priority = entry.last_accessed - (entry.access_count * 10)
return entry.value
async def delete(self, key: str) -> bool:
"""Delete entry from cache."""
async with self._lock:
entry = self._store.pop(key, None)
if entry:
self._total_tokens -= entry.token_count
return True
return False
async def _apply_eviction_policy(self) -> int:
"""
Apply eviction policy based on current mode.
Returns:
Number of entries evicted
"""
evicted = 0
now = time.monotonic()
async with self._lock:
match self._mode:
case EvictionMode.RELAXED:
pass # No eviction
case EvictionMode.NORMAL:
# LRU: evict entries idle > 120s
to_evict = [
k for k, e in self._store.items()
if now - e.last_accessed > 120
]
for k in to_evict:
self._evict(k)
evicted += 1
case EvictionMode.PRESSURE:
# LFU by token_count: evict heaviest, least used first
candidates = sorted(
self._store.values(),
key=lambda e: e.token_count / max(e.access_count, 1),
reverse=True
)
# Evict top 25%
target = max(1, int(len(candidates) * 0.25))
for entry in candidates[:target]:
self._evict(entry.key)
evicted += 1
case EvictionMode.CRITICAL:
# Mark inactive for CPU offload instead of destroying
for entry in self._store.values():
if now - entry.last_accessed > 30 and not entry.offloaded_to_cpu:
entry.offloaded_to_cpu = True
case EvictionMode.EMERGENCY:
# Hard evict everything idle > 30s
to_evict = [
k for k, e in self._store.items()
if now - e.last_accessed > 30
]
for k in to_evict:
self._evict(k)
evicted += 1
if evicted > 0:
await self._reheap()
return evicted
def _evict(self, key: str) -> None:
"""Remove entry. Must be called under lock."""
entry = self._store.pop(key, None)
if entry:
self._total_tokens -= entry.token_count
async def _reheap(self) -> None:
"""Rebuild heap after evictions."""
self._heap = list(self._store.values())
heapq.heapify(self._heap)
async def clear(self) -> None:
"""Clear all entries."""
async with self._lock:
self._store.clear()
self._heap.clear()
self._total_tokens = 0
@property
def size(self) -> int:
"""Number of entries."""
return len(self._store)
@property
def total_tokens(self) -> int:
"""Total token count in cache."""
return self._total_tokens
@property
def mode(self) -> EvictionMode:
"""Current eviction mode."""
return self._mode
@property
def is_blocked(self) -> bool:
"""True if new registrations are blocked (EMERGENCY mode)."""
return self._blocked
|