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

f48c6791 · Zhuohan Li · GitHub · c2c5e090 · f48c6791
Unverified Commit f48c6791 authored Mar 08, 2024 by Zhuohan Li Committed by GitHub Mar 08, 2024
Show whitespace changes
Inline Side-by-side

Showing with 0 additions and 2 deletions

vllm/model_executor/layers/attention/backends/flash_attn.py vllm/model_executor/layers/attention/backends/flash_attn.py +0 -2

No files found.
--- 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: