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

[refactor] remove redundant code in linear

Browse Source
This commit is contained in:
Li Wei
2025-12-24 12:02:09 +08:00
parent 75d0bdae2f
commit 383eb5459a
8 changed files with 37 additions and 1570 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_kunlun/models/qwen3.py
View File

@@ -38,7 +38,7 @@ from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
from vllm.logger import init_logger
from vllm.model_executor.layers.layernorm import RMSNorm
from vllm_kunlun.ops.linear import (QKVParallelLinear,
from vllm.model_executor.layers.linear import (QKVParallelLinear,
RowParallelLinear)
from vllm.model_executor.layers.logits_processor import LogitsProcessor
from vllm.model_executor.layers.quantization import QuantizationConfig