[Bugfix] fix sleepmode level2 e2e test (#4019)
### What this PR does / why we need it?
enable sleepmode level2 e2e test and add the check logic to ensure the
nz is not enabled.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
use e2e tests
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: wangx700 <wangxin700@huawei.com>
This commit is contained in:
@@ -47,7 +47,7 @@ from vllm_ascend.cpu_binding import bind_cpus
|
||||
from vllm_ascend.device_allocator.camem import CaMemAllocator
|
||||
from vllm_ascend.distributed.parallel_state import init_ascend_model_parallel
|
||||
from vllm_ascend.platform import NPUPlatform
|
||||
from vllm_ascend.utils import (init_ascend_soc_version,
|
||||
from vllm_ascend.utils import (init_ascend_soc_version, is_enable_nz,
|
||||
prefill_context_parallel_enable,
|
||||
register_ascend_customop, sleep_mode_enabled,
|
||||
try_register_lib, vllm_version_is)
|
||||
@@ -184,6 +184,11 @@ class NPUWorker(WorkerBase):
|
||||
raise ValueError(
|
||||
"Sleep mode is not enabled. Please compile vllm-ascend with COMPILE_CUSTOM_KERNELS=1."
|
||||
)
|
||||
|
||||
if is_enable_nz():
|
||||
raise ValueError(
|
||||
"FRACTAL_NZ mode is enabled. This may cause model parameter precision issues "
|
||||
"in the RL scenarios. Please set VLLM_ASCEND_ENABLE_NZ=0.")
|
||||
allocator = CaMemAllocator.get_instance()
|
||||
allocator.wake_up(tags=tags)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user