A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 04:15 UTC
[FIX] Fix prefix test error on main (#3286)
Zhuohan Li committed
Mar 8, 2024 at 17:16 UTC
f48c6791b7bfc2579ad575d33ed83912f0bfb011
1 file changed
-2
vllm/model_executor/layers/attention/backends/flash_attn.py
-2
@@ -103,8 +103,6 @@ class FlashAttentionBackend:
103
key_cache,
104
value_cache,
105
input_metadata,
106
- self.num_heads,
107
- self.num_kv_heads,
106
self.alibi_slopes,
107
)
108
else: