Merge pull request #59 from liwei109/aicapx-quant

[fix]remove weight_loader_v2 to suport cuda graph
2025-12-29 19:56:24 +08:00
parent 7fb627c34e
commit 9cee025f41
2 changed files with 28 additions and 16 deletions
--- a/vllm_kunlun/ops/init.py
+++ b/vllm_kunlun/ops/init.py
@@ -15,6 +15,7 @@
 # This file is a part of the vllm-ascend project.
 #

+# import vllm_kunlun.ops.linear
 import vllm_kunlun.ops.rotary_embedding
 import vllm_kunlun.ops.layernorm
 import vllm_kunlun.ops.quantization.awq