[misc] update tpu int8 to use new vLLM Parameters (#7973)

2024-08-29 16:46:55 -04:00
parent d78789ac16
commit 86a677de42
2 changed files with 13 additions and 11 deletions
--- a/vllm/model_executor/layers/linear.py
+++ b/vllm/model_executor/layers/linear.py
@@ -23,7 +23,8 @@ logger = init_logger(__name__)
 WEIGHT_LOADER_V2_SUPPORTED = [
    "CompressedTensorsLinearMethod", "AWQMarlinLinearMethod",
    "AWQLinearMethod", "GPTQMarlinLinearMethod", "Fp8LinearMethod",
-    "MarlinLinearMethod", "QQQLinearMethod", "GPTQMarlin24LinearMethod"
+    "MarlinLinearMethod", "QQQLinearMethod", "GPTQMarlin24LinearMethod",
+    "TPUInt8LinearMethod"
 ]