[Bugfix] fix dcp_only bug and add e2e accuracy test for dcp only and pcp only (#5565)
### What this PR does / why we need it?
[Bugfix] fix dcp_only bug and add e2e accuracy test for dcp only and pcp
only
this pr fix the bug of accuracy test when decode_parallel_size>1 and
prefill_context_parallel_size=1.
### Does this PR introduce _any_ user-facing change?
NO
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
7157596103
---------
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
This commit is contained in:
@@ -13,6 +13,8 @@
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
from vllm.v1.worker.workspace import init_workspace_manager
|
||||
|
||||
from vllm_ascend.worker.worker import NPUWorker
|
||||
from vllm_ascend.xlite.xlite_model_runner import XliteModelRunner
|
||||
|
||||
@@ -23,4 +25,6 @@ class XliteWorker(NPUWorker):
|
||||
def init_device(self):
|
||||
"""Override init_device to init xlite model runner"""
|
||||
self.device = self._init_device()
|
||||
num_ubatches = 1
|
||||
init_workspace_manager(self.device, num_ubatches)
|
||||
self.model_runner = XliteModelRunner(self.vllm_config, self.device)
|
||||
|
||||
Reference in New Issue
Block a user