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 marlin config repr (#3414)
Enrique Shockwave committed
Mar 14, 2024 at 23:26 UTC
b983ba35bd29f6d385efff8bedf80f7989c28d12
1 file changed
+1
-1
vllm/model_executor/layers/quantization/marlin.py
+1
-1
@@ -47,7 +47,7 @@ class MarlinConfig(QuantizationConfig):
47
self.perm_len = 1024
48
49
def __repr__(self) -> str:
50
- return f"MarlinConfig(group_size={self.group_size}"
50
+ return f"MarlinConfig(group_size={self.group_size})"
51
52
@classmethod
53
def get_name(cls) -> str: