[Core] Multiprocessing Pipeline Parallel support (#6130)
Co-authored-by: Murali Andoorveedu <muralidhar.andoorveedu@centml.ai>
This commit is contained in:
co-authored by
Murali Andoorveedu
parent
c5df56f88b
commit
b5672a112c
@@ -1,4 +1,3 @@
|
||||
import asyncio
|
||||
from abc import ABC, abstractmethod
|
||||
from typing import List, Optional, Set, Tuple
|
||||
|
||||
@@ -132,26 +131,6 @@ class ExecutorBase(ABC):
|
||||
|
||||
class ExecutorAsyncBase(ExecutorBase):
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
model_config: ModelConfig,
|
||||
cache_config: CacheConfig,
|
||||
parallel_config: ParallelConfig,
|
||||
scheduler_config: SchedulerConfig,
|
||||
device_config: DeviceConfig,
|
||||
load_config: LoadConfig,
|
||||
lora_config: Optional[LoRAConfig],
|
||||
multimodal_config: Optional[MultiModalConfig],
|
||||
speculative_config: Optional[SpeculativeConfig],
|
||||
prompt_adapter_config: Optional[PromptAdapterConfig],
|
||||
) -> None:
|
||||
self.pp_locks: Optional[List[asyncio.Lock]] = None
|
||||
|
||||
super().__init__(model_config, cache_config, parallel_config,
|
||||
scheduler_config, device_config, load_config,
|
||||
lora_config, multimodal_config, speculative_config,
|
||||
prompt_adapter_config)
|
||||
|
||||
@abstractmethod
|
||||
async def execute_model_async(
|
||||
self,
|
||||
|
||||
Reference in New Issue
Block a user