[Feature] Support XiaoMi MIMO Flash V2 (#62)

* [Feature] Support MIMO Flash V2
2025-12-31 10:16:33 +08:00
parent 341dc7f296
commit b3c30a3cb9
12 changed files with 1530 additions and 690 deletions
--- a/vllm_kunlun/ops/init.py
+++ b/vllm_kunlun/ops/init.py
@@ -15,8 +15,8 @@
 # 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
-import vllm_kunlun.ops.quantization.gptq
+import vllm_kunlun.ops.quantization.gptq
+import vllm_kunlun.ops.vocab_parallel_embedding