Upgrade to new vllm commit (#3719)
### What this PR does / why we need it? Upgrade to new vllm commit:c9461e05a4- Fix many imports, caused by https://github.com/vllm-project/vllm/pull/26908 - Fix import ```sha256```, caused by https://github.com/vllm-project/vllm/pull/27169 - Remove ```SchedulerConfig.send_delta_data```, caused by https://github.com/vllm-project/vllm/pull/27142 - Fix ```FusedMoE``` because of dual stream execution, caused by https://github.com/vllm-project/vllm/pull/26440 ### Does this PR introduce _any_ user-facing change? N/A ### How was this patch tested? CI passed with new added/existing test. - vLLM version: v0.11.0rc3 - vLLM main:17c540a993--------- Signed-off-by: MengqingCao <cmq0113@163.com> Signed-off-by: Icey <1790571317@qq.com> Co-authored-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
@@ -25,19 +25,25 @@ from vllm.distributed.kv_transfer.kv_connector.v1.base import (
|
||||
from vllm.distributed.parallel_state import (get_dcp_group, get_tp_group,
|
||||
get_world_group)
|
||||
from vllm.forward_context import ForwardContext
|
||||
from vllm.utils import get_ip, logger
|
||||
from vllm.utils import logger
|
||||
from vllm.v1.core.kv_cache_manager import KVCacheBlocks
|
||||
from vllm.v1.core.sched.output import SchedulerOutput
|
||||
from vllm.v1.request import Request, RequestStatus
|
||||
|
||||
import vllm_ascend.envs as envs_ascend
|
||||
from vllm_ascend.utils import (AscendSocVersion, get_ascend_soc_version,
|
||||
prefill_context_parallel_enable)
|
||||
prefill_context_parallel_enable,
|
||||
vllm_version_is)
|
||||
|
||||
if prefill_context_parallel_enable():
|
||||
from vllm.distributed.parallel_state import \
|
||||
get_prefill_context_model_parallel_rank
|
||||
|
||||
if vllm_version_is("0.11.0"):
|
||||
from vllm.utils import get_ip
|
||||
else:
|
||||
from vllm.utils.network_utils import get_ip
|
||||
|
||||
TORCH_DTYPE_TO_NPU_DTYPE = {
|
||||
torch.half: llm_datadist.DataType.DT_FLOAT16,
|
||||
torch.float16: llm_datadist.DataType.DT_FLOAT16,
|
||||
|
||||
Reference in New Issue
Block a user