We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
2 parents 089e617 + db87ade commit 0bb6c7cCopy full SHA for 0bb6c7c
lightllm/server/router/model_infer/mode_backend/mtp_pre_process.py
@@ -1,12 +1,7 @@
1
import torch
2
import copy
3
-from typing import List, Tuple
4
-from lightllm.server.router.model_infer.infer_batch import InferReq
5
-from lightllm.common.basemodel.batch_objs import ModelInput, ModelOutput
6
-from lightllm.server.router.model_infer.infer_batch import g_infer_context
7
-from lightllm.common.basemodel.infer_lock import g_infer_state_lock
+from lightllm.common.basemodel.batch_objs import ModelInput
8
from lightllm.common.basemodel.triton_kernel.gen_mtp_prefill_params import gen_mtp_new_input_ids
9
-from lightllm.utils.dist_utils import get_current_device_id
10
11
12
def prepare_mtp_prefill_inputs(
0 commit comments