[AMD] Add Kimi K2.5 INT4 single-node MI325X vLLM benchmark (TP8)

.github/configs/amd-master.yaml

@@ -315,6 +315,28 @@ kimik2.5-int4-mi355x-vllm:
     search-space:
     - { tp: 8, conc-start: 4, conc-end: 64 }
 
+kimik2.5-int4-mi325x-vllm:
+  image: vllm/vllm-openai-rocm:v0.16.0
+  model: moonshotai/Kimi-K2.5
+  model-prefix: kimik2.5
+  runner: mi325x
+  precision: int4
+  framework: vllm
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 64 }
+  - isl: 1024
+    osl: 8192
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 64 }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 8, conc-start: 4, conc-end: 64 }
+
 kimik2.5-fp4-mi355x-vllm:
   image: vllm/vllm-openai-rocm:v0.16.0
   model: amd/Kimi-K2.5-MXFP4

benchmarks/single_node/kimik2.5_int4_mi325x.sh

@@ -0,0 +1,64 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    MAX_MODEL_LEN \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+hf download "$MODEL"
+
+# Set HIP_VISIBLE_DEVICES to match ROCR_VISIBLE_DEVICES for Ray compatibility in vLLM 0.14+
+if [ -n "$ROCR_VISIBLE_DEVICES" ]; then
+    export HIP_VISIBLE_DEVICES="$ROCR_VISIBLE_DEVICES"
+fi
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+# following AMD andy luo's recipe
+# https://x.com/linluo77/status/2017024513595301985
+set -x
+vllm serve $MODEL --port $PORT \
+--tensor-parallel-size=$TP \
+--gpu-memory-utilization 0.95 \
+--max-model-len $MAX_MODEL_LEN \
+--block-size=64 \
+--disable-log-requests \
+--trust-remote-code \
+--mm-encoder-tp-mode data > $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+run_benchmark_serving \
+    --model "$MODEL" \
+    --port "$PORT" \
+    --backend vllm \
+    --input-len "$ISL" \
+    --output-len "$OSL" \
+    --random-range-ratio "$RANDOM_RANGE_RATIO" \
+    --num-prompts "$((CONC * 10))" \
+    --max-concurrency "$CONC" \
+    --result-filename "$RESULT_FILENAME" \
+    --result-dir /workspace/ \
+    --trust-remote-code
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT" --concurrent-requests $CONC
+    append_lm_eval_summary
+fi
+set +x

perf-changelog.yaml

@@ -1,3 +1,10 @@
+- config-keys:
+    - kimik2.5-int4-mi325x-vllm
+  description:
+    - "Add Kimi K2.5 INT4 single-node MI325X vLLM benchmark (TP8)"
+    - "Uses vLLM ROCm v0.16.0 image following AMD Andy Luo's recipe"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/857
+
 - config-keys:
     - 70b-fp8-*-vllm
   description:

runners/launch_mi325x-amd.sh

@@ -9,7 +9,7 @@ LOCK_FILE="${SQUASH_FILE}.lock"
 
 set -x
 
-JOB_ID=$(salloc --partition=$PARTITION --gres=gpu:$TP --cpus-per-task=256 --time=180 --no-shell --job-name="$RUNNER_NAME" 2>&1 | tee /dev/stderr | grep -oP 'Granted job allocation \K[0-9]+')
+JOB_ID=$(salloc --partition=$PARTITION --gres=gpu:$TP --cpus-per-task=256 --time=480 --no-shell --job-name="$RUNNER_NAME" 2>&1 | tee /dev/stderr | grep -oP 'Granted job allocation \K[0-9]+')
 
 if [ -z "$JOB_ID" ]; then
     echo "ERROR: salloc failed to allocate a job"