diff --git a/benchmarks/single_node/dsr1_fp8_mi300x.sh b/benchmarks/single_node/dsr1_fp8_mi300x.sh
index a5f161960..3dbff11e4 100644
--- a/benchmarks/single_node/dsr1_fp8_mi300x.sh
+++ b/benchmarks/single_node/dsr1_fp8_mi300x.sh
@@ -48,10 +48,10 @@ set -x
 python3 -m sglang.launch_server \
 --model-path=$MODEL --host=0.0.0.0 --port=$PORT --trust-remote-code \
 --tensor-parallel-size=$TP \
---mem-fraction-static=0.8 \
+--mem-fraction-static=0.85 \
 --cuda-graph-max-bs=128 \
 --chunked-prefill-size=131072 \
---num-continuous-decode-steps=4 \
+--num-continuous-decode-steps=16 \
 --max-prefill-tokens=131072 \
 --kv-cache-dtype fp8_e4m3 \
 --attention-backend aiter \
diff --git a/benchmarks/single_node/kimik2.5_int4_mi300x.sh b/benchmarks/single_node/kimik2.5_int4_mi300x.sh
index a05baddeb..dc11bf27a 100755
--- a/benchmarks/single_node/kimik2.5_int4_mi300x.sh
+++ b/benchmarks/single_node/kimik2.5_int4_mi300x.sh
@@ -45,7 +45,7 @@ vllm serve $MODEL --port $PORT \
 --block-size=64 \
 --trust-remote-code \
 --no-enable-prefix-caching \
---max-num-seqs 256 \
+--max-num-seqs 128 \
 --mm-encoder-tp-mode data > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 16fea938d..1beb14f9e 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1,3 +1,15 @@
+- config-keys:
+    - kimik2.5-int4-mi300x-vllm
+  description:
+    - "Tune --max-num-seqs 256 → 128 (+34.2% avg output throughput gain)"
+  pr-link: TBD
+
+- config-keys:
+    - dsr1-fp8-mi300x-sglang
+  description:
+    - "Tune --mem-fraction-static 0.8 → 0.85, --num-continuous-decode-steps 4 → 16 (+4.2% avg output throughput gain)"
+  pr-link: TBD
+
 - config-keys:
     - kimik2.5-fp4-gb200-dynamo-trt
   description: