remove qwen2.py llama.py fix llama output

2025-12-31 11:31:26 +08:00
parent b3c30a3cb9
commit b015bb76fd
11 changed files with 65 additions and 1263 deletions
--- a/vllm_kunlun/ops/init.py
+++ b/vllm_kunlun/ops/init.py
@@ -19,4 +19,5 @@ import vllm_kunlun.ops.rotary_embedding
 import vllm_kunlun.ops.layernorm
 import vllm_kunlun.ops.quantization.awq
 import vllm_kunlun.ops.quantization.gptq
-import vllm_kunlun.ops.vocab_parallel_embedding
+import vllm_kunlun.ops.vocab_parallel_embedding
+import vllm_kunlun.ops.linear