[FIX] Fix prefix test error on main (#3286)

2024-03-08 17:16:14 -08:00
parent c2c5e0909a
commit f48c6791b7
1 changed files with 0 additions and 2 deletions
--- a/vllm/model_executor/layers/attention/backends/flash_attn.py
+++ b/vllm/model_executor/layers/attention/backends/flash_attn.py
@@ -103,8 +103,6 @@ class FlashAttentionBackend:
                    key_cache,
                    value_cache,
                    input_metadata,
-                    self.num_heads,
-                    self.num_kv_heads,
                    self.alibi_slopes,
                )
        else: