[Misc] Update qqq to use vLLMParameters (#7805)

2024-08-26 15:16:15 -04:00
parent 2deb029d11
commit 665304092d
3 changed files with 54 additions and 64 deletions
--- a/vllm/model_executor/layers/linear.py
+++ b/vllm/model_executor/layers/linear.py
@@ -23,7 +23,7 @@ logger = init_logger(__name__)
 WEIGHT_LOADER_V2_SUPPORTED = [
    "CompressedTensorsLinearMethod", "AWQMarlinLinearMethod",
    "AWQLinearMethod", "GPTQMarlinLinearMethod", "Fp8LinearMethod",
-    "MarlinLinearMethod"
+    "MarlinLinearMethod", "QQQLinearMethod"
 ]