[EASY] Drop duplicate KV-cache initialization (#38799)

Signed-off-by: namgyu-youn <namgyu.dev@gmail.com>
2026-04-07 03:05:39 +09:00
parent 419e73cdfa
commit 94fbb09894
1 changed files with 0 additions and 3 deletions
--- a/vllm/model_executor/layers/attention/attention.py
+++ b/vllm/model_executor/layers/attention/attention.py
@@ -131,9 +131,6 @@ def _init_kv_cache_quant(
        quant_config: Optional quantization configuration.
        prefix: Layer name prefix for quantization method lookup.
    """
-    quant_method = (
-        quant_config.get_quant_method(layer, prefix=prefix) if quant_config else None
-    )

    # Note [Register q/k/v/prob scales in state dict]
    # When calling model.to(device), only parameters/buffers in state dict are