EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Drop 0.11.0 support (#4377)

Browse Source 
There is a lot hack code for v0.11.0, which makes the code hard to
upgrade to newer vLLM version. Since v0.11.0 will release soon. Let's
drop v0.11.0 support first. Then we'll upgrade to v0.11.2 soon.


- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-11-24 17:08:20 +08:00
committed by GitHub
parent 41ddb06554
commit a1f142b7ad
80 changed files with 467 additions and 1755 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
vllm_ascend/distributed/mooncake/mooncake_engine.py
View File

@@ -8,6 +8,7 @@ from typing import Generator, List, Optional, Union
import torch
from vllm.config import VllmConfig
from vllm.utils import logger
from vllm.utils.torch_utils import get_kv_cache_torch_dtype
from vllm_ascend.distributed.mooncake.config_data import (
ChunkedTokenDatabase, LasyerMultiBlockReqMeta, MooncakeConnectorMetadata,
@@ -16,12 +17,6 @@ from vllm_ascend.distributed.mooncake.kv_transfer import (
KVCacheStoreLayerRecvingThread, KVCacheStoreLayerSendingThread,
KVCacheStoreRecvingThread, KVCacheStoreSendingThread, KVTransferThread)
from vllm_ascend.distributed.mooncake.mooncake_store import Mooncakestore
from vllm_ascend.utils import vllm_version_is
if vllm_version_is("0.11.0"):
from vllm.utils import get_kv_cache_torch_dtype
else:
from vllm.utils.torch_utils import get_kv_cache_torch_dtype
class MooncakeEngine: