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 15, 09:45 UTC
[Misc] Fix typo (#18330)
Gong Shufan committed
May 20, 2025 at 00:51 UTC
81712218341ce09d555579829e8903e7a9aa4880
1 file changed
+1
-1
examples/lmcache/disagg_prefill_lmcache_v1/disagg_vllm_launcher.sh
+1
-1
@@ -54,6 +54,6 @@ elif [[ $1 == "decoder" ]]; then
54
55
else
56
echo "Invalid role: $1"
57
- echo "Should be either prefill, decode"
57
+ echo "Should be either prefiller, decoder"
58
exit 1
59
fi