diff --git a/benchmarks/single_node/kimik2.5_fp4_b200.sh b/benchmarks/single_node/kimik2.5_fp4_b200.sh
index 422a74950..d08e23bb2 100644
--- a/benchmarks/single_node/kimik2.5_fp4_b200.sh
+++ b/benchmarks/single_node/kimik2.5_fp4_b200.sh
@@ -38,6 +38,7 @@ vllm serve $MODEL --host 0.0.0.0 --port $PORT \
 --reasoning-parser kimi_k2 \
 --tool-call-parser kimi_k2 \
 --compilation_config.pass_config.fuse_allreduce_rms true \
+--no-enable-prefix-caching \
 --trust-remote-code > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!
diff --git a/benchmarks/single_node/kimik2.5_fp4_mi355x.sh b/benchmarks/single_node/kimik2.5_fp4_mi355x.sh
index a8bd01442..967003232 100755
--- a/benchmarks/single_node/kimik2.5_fp4_mi355x.sh
+++ b/benchmarks/single_node/kimik2.5_fp4_mi355x.sh
@@ -70,6 +70,7 @@ $EP \
 --block-size=1 \
 --no-enable-prefix-caching \
 --trust-remote-code \
+--no-enable-prefix-caching \
 --mm-encoder-tp-mode data > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!
diff --git a/benchmarks/single_node/kimik2.5_int4_h200.sh b/benchmarks/single_node/kimik2.5_int4_h200.sh
index 37281f61e..473a1bd73 100755
--- a/benchmarks/single_node/kimik2.5_int4_h200.sh
+++ b/benchmarks/single_node/kimik2.5_int4_h200.sh
@@ -40,6 +40,7 @@ vllm serve $MODEL --host 0.0.0.0 --port $PORT \
 --tool-call-parser kimi_k2 \
 --compilation_config.pass_config.fuse_allreduce_rms true \
 --trust-remote-code \
+--no-enable-prefix-caching \
 --disable-log-requests > $SERVER_LOG 2>&1 &
 
 SERVER_PID=$!
diff --git a/benchmarks/single_node/kimik2.5_int4_mi325x.sh b/benchmarks/single_node/kimik2.5_int4_mi325x.sh
index 8ca56dc29..1a42035a0 100755
--- a/benchmarks/single_node/kimik2.5_int4_mi325x.sh
+++ b/benchmarks/single_node/kimik2.5_int4_mi325x.sh
@@ -40,6 +40,7 @@ vllm serve $MODEL --port $PORT \
 --max-model-len $MAX_MODEL_LEN \
 --block-size=64 \
 --trust-remote-code \
+--no-enable-prefix-caching \
 --max-num-seqs 256 \
 --mm-encoder-tp-mode data > $SERVER_LOG 2>&1 &
 
diff --git a/benchmarks/single_node/kimik2.5_int4_mi355x.sh b/benchmarks/single_node/kimik2.5_int4_mi355x.sh
index 935c6cd2e..420f8044a 100755
--- a/benchmarks/single_node/kimik2.5_int4_mi355x.sh
+++ b/benchmarks/single_node/kimik2.5_int4_mi355x.sh
@@ -37,6 +37,7 @@ vllm serve $MODEL --port $PORT \
 --max-model-len $MAX_MODEL_LEN \
 --block-size=64 \
 --trust-remote-code \
+--no-enable-prefix-caching \
 --max-num-seqs 256 \
 --mm-encoder-tp-mode data > $SERVER_LOG 2>&1 &
 
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 6a8a6e666..3e7db64e5 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1108,3 +1108,13 @@
   description:
     - "Update vLLM image from v0.15.1 to v0.18.0 for gptoss H100 and H200 configs"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/960
+
+- config-keys:
+    - kimik2.5-int4-mi325x-vllm
+    - kimik2.5-int4-mi355x-vllm
+    - kimik2.5-int4-h200-vllm
+    - kimik2.5-fp4-mi355x-vllm
+    - kimik2.5-fp4-b200-vllm
+  description:
+    - "Disable prefix caching (--no-enable-prefix-caching) for all Kimi K2.5 benchmarks using random datasets"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/926
diff --git a/runners/launch_h200-nb.sh b/runners/launch_h200-nb.sh
index 170a1bdc3..9d157a858 100644
--- a/runners/launch_h200-nb.sh
+++ b/runners/launch_h200-nb.sh
@@ -1,6 +1,6 @@
 #!/usr/bin/bash
 
-export HF_HUB_CACHE_MOUNT="/home/gharunner/gharunners/hf-hub-cache/"
+export HF_HUB_CACHE_MOUNT="/mnt/data/gharunners/hf-hub-cache/"
 export PORT=8888
 
 MODEL_CODE="${EXP_NAME%%_*}"