Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)

Co-authored-by: SangBin Cho <rkooo567@gmail.com>
Co-authored-by: dhou-xai <dhou@x.ai>
Co-authored-by: Hanming Lu <hanming_lu@berkeley.edu>

scripts/killall_sglang.sh

@@ -1,14 +1,5 @@
 #!/bin/bash
 
-# Check if sudo is available
-if command -v sudo >/dev/null 2>&1; then
-    sudo apt-get update
-    sudo apt-get install -y lsof
-else
-    apt-get update
-    apt-get install -y lsof
-fi
-
 # Show current GPU status
 nvidia-smi
 
@@ -20,6 +11,14 @@ kill -9 $(ps aux | grep 'sglang.data_parallel' | grep -v 'grep' | awk '{print $2
 
 # Clean all GPU processes if any argument is provided
 if [ $# -gt 0 ]; then
+    # Check if sudo is available
+    if command -v sudo >/dev/null 2>&1; then
+        sudo apt-get update
+        sudo apt-get install -y lsof
+    else
+        apt-get update
+        apt-get install -y lsof
+    fi
     kill -9 $(nvidia-smi | sed -n '/Processes:/,$p' | grep "   [0-9]" | awk '{print $5}') 2>/dev/null
     lsof /dev/nvidia* | awk '{print $2}' | xargs kill -9 2>/dev/null
 fi