ef6abf3dc7
Adds ALL files needed for Dockerfile build:
- qwen3_6_scripts/ (baseline patches + our optimizations)
- vllm/ (full vllm package)
- paged_attention_v2_pytorch.py (V2 with single-bmm optimization)
- Dockerfile + computility-run.yaml
Our optimizations vs baseline:
1. paged_attn.py: pre-gathered context KV (eliminates 194 gather calls),
Triton try/fallback, V2 heuristic, threshold 32K→64K
2. paged_attention_v2_pytorch.py: fills NotImplementedError,
single-bmm Phase 1 (195 launches → 3)
3. patch_enable_triton.py: HAS_TRITON=True with safety fallback
4. patch_triton_tuning.py: BLOCK=64, NUM_WARPS=4 for BI-V100
5. computility-run.yaml: gpu-memory-utilization 0.9→0.95,
max-num-batched-tokens 8192→16384
This repo can now be submitted to dev.modelhub.org.cn as-is.
105 lines
2.8 KiB
Python
105 lines
2.8 KiB
Python
from abc import ABC, abstractmethod
|
|
from typing import Any, Callable, Dict, Hashable, Optional, TypeVar
|
|
|
|
from torch import nn
|
|
|
|
from vllm.logger import init_logger
|
|
from vllm.utils import LRUCache
|
|
|
|
logger = init_logger(__name__)
|
|
|
|
|
|
class AdapterModel(ABC):
|
|
|
|
def __init__(self, model_id=None):
|
|
self.id = model_id
|
|
|
|
@abstractmethod
|
|
def from_local_checkpoint(cls, model_dir, model_id=None, **kwargs):
|
|
# Common initialization code
|
|
# Load weights or embeddings from local checkpoint
|
|
raise NotImplementedError("Subclasses must implement this method.")
|
|
|
|
|
|
T = TypeVar('T')
|
|
|
|
|
|
class AdapterLRUCache(LRUCache[T]):
|
|
|
|
def __init__(self, capacity: int, deactivate_fn: Callable[[Hashable],
|
|
None]):
|
|
super().__init__(capacity)
|
|
self.deactivate_fn = deactivate_fn
|
|
|
|
def _on_remove(self, key: Hashable, value: Optional[T]):
|
|
logger.debug("Removing adapter int id: %d", key)
|
|
self.deactivate_fn(key)
|
|
return super()._on_remove(key, value)
|
|
|
|
|
|
class AdapterModelManager(ABC):
|
|
|
|
def __init__(
|
|
self,
|
|
model: nn.Module,
|
|
):
|
|
"""Create a AdapterModelManager and adapter for a given model.
|
|
Args:
|
|
model: the model to be adapted.
|
|
"""
|
|
self.model: nn.Module = model
|
|
self._registered_adapters: Dict[int, Any] = {}
|
|
# Dict instead of a Set for compatibility with LRUCache.
|
|
self._active_adapters: Dict[int, None] = {}
|
|
self.adapter_type = 'Adapter'
|
|
self._last_mapping = None
|
|
|
|
def __len__(self) -> int:
|
|
return len(self._registered_adapters)
|
|
|
|
@property
|
|
@abstractmethod
|
|
def adapter_slots(self) -> int:
|
|
raise NotImplementedError
|
|
|
|
@property
|
|
@abstractmethod
|
|
def capacity(self) -> int:
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
def activate_adapter(self, adapter_id: int) -> bool:
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
def deactivate_adapter(self, adapter_id: int) -> bool:
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
def add_adapter(self, adapter: Any) -> bool:
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
def set_adapter_mapping(self, mapping: Any) -> None:
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
def remove_adapter(self, adapter_id: int) -> bool:
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
def remove_all_adapters(self) -> None:
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
def get_adapter(self, adapter_id: int) -> Optional[Any]:
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
def list_adapters(self) -> Dict[int, Any]:
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
def pin_adapter(self, adapter_id: int) -> bool:
|
|
raise NotImplementedError
|