kimik3-fp4-mi355x-vllm-agentic-mtp: add LMCache DRAM KV-offload arm

benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh

@@ -109,12 +109,14 @@
 mkdir -p "$RESULT_DIR"
 
 SERVER_PID=""
+LMCACHE_PID=""
 
 cleanup_agentic_services() {
     local exit_code=$?
     trap - EXIT INT TERM
     set +e
     stop_background_process_tree "$SERVER_PID" "vLLM server" 60
+    stop_background_process_tree "$LMCACHE_PID" "LMCache server"
     exit "$exit_code"
 }
 trap cleanup_agentic_services EXIT
@@ -143,6 +145,77 @@
     )
     echo "SimpleCPUOffloadConnector: ${CPU_BYTES_PER_RANK} B/rank x ${TP} ranks, lazy_offload=$SIMPLE_LAZY_OFFLOAD"
     ;;
+  lmcache)
+    require_agentic_kv_offload_backend "$KV_OFFLOAD_BACKEND"
+
+    # Keep the image's tested torch/ROCm stack and install only LMCache's
+    # missing runtime dependencies, same as the MiniMax-M3 lmcache arm.
+    LMCACHE_VERSION="0.5.4rc2"
+    LMCACHE_ROCM_INDEX="https://github.com/LMCache/LMCache/releases/expanded_assets/v${LMCACHE_VERSION}-rocm"
+    agentic_pip_install --quiet --no-cache-dir --no-deps \
+        "sortedcontainers==2.4.0" \
+        "opentelemetry-exporter-prometheus==0.61b0" \
+        "cupy-rocm-7-0==14.1.1" \
+        "lmcache==${LMCACHE_VERSION}" --find-links "$LMCACHE_ROCM_INDEX"
+    python3 -c \
+        "import cupy; import lmcache.integration.vllm.lmcache_mp_connector; import opentelemetry.exporter.prometheus" \
+        >/dev/null
+
+    # One MP server for the node, per the Kimi-K3 recipe
+    # (docs.lmcache.ai/recipes/kimi_k3.html), with --chunk-size sized for
+    # THIS stack rather than the recipe's CUDA-path 768: the connector
+    # requires the chunk to be a multiple of every engine KV group's
+    # tokens_per_block, and the hybrid KDA/MLA layout here registers
+    # attention groups at 1536 ("Setting attention block size to 1536",
+    # run 31644990546) plus a KDA state group at 3072 (run 31645828378),
+    # so 3072 is the minimum valid chunk. The multi-group layout also
+    # requires one object group per sliding-window size:
+    # --separate-object-groups.
+    LMCACHE_PORT=6555
+    LMCACHE_HTTP_PORT=8090
+    LMCACHE_LOG="$RESULT_DIR/lmcache_server.log"
+
+    LMCACHE_L1_SIZE_GB="$TOTAL_CPU_DRAM_GB"
+
+    LMCACHE_CMD=(
+        lmcache server
+        --host 127.0.0.1
+        --port "$LMCACHE_PORT"
+        --http-host 127.0.0.1
+        --http-port "$LMCACHE_HTTP_PORT"
+        --l1-size-gb "$LMCACHE_L1_SIZE_GB"
+        --l1-init-size-gb 10
+        --chunk-size 3072
+        --separate-object-groups
+        --enable-extra-logging
+        --extra-logging-interval 30
+        --max-cpu-workers 8
+        --max-gpu-workers 1
+        --eviction-policy LRU
+        --supported-transfer-mode lmcache_driven
+        --shm-name ""
+    )
+    append_command "$RESULT_DIR/lmcache_command.txt" "${LMCACHE_CMD[@]}"
+    "${LMCACHE_CMD[@]}" > "$LMCACHE_LOG" 2>&1 &
+    LMCACHE_PID=$!
+    wait_for_ready \
+        --endpoint "http://127.0.0.1:${LMCACHE_HTTP_PORT}/healthcheck" \
+        --log "$LMCACHE_LOG" \
+        --pid "$LMCACHE_PID" \
+        --sleep-interval 1 \
+        --timeout 600
+
+    # 100k-330k-token agentic prefixes make single retrieves large; use the
+    # same MQ timeout headroom as the MiniMax-M3 arm.
+    OFFLOAD_ARGS=(
+        --kv-transfer-config
+        "{\"kv_connector\":\"LMCacheMPConnector\",\"kv_connector_module_path\":\"lmcache.integration.vllm.lmcache_mp_connector\",\"kv_role\":\"kv_both\",\"kv_connector_extra_config\":{\"lmcache.mp.port\":$LMCACHE_PORT,\"lmcache.mp.mq_timeout\":6000.0}}"
+    )
+    ;;
+  *)
+    echo "Error: unsupported KV_OFFLOAD_BACKEND='$KV_OFFLOAD_BACKEND' (expected vllm-simple or lmcache)" >&2
+    exit 1
+    ;;
 esac
 fi
 

configs/amd-master.yaml

@@ -651,6 +651,28 @@ kimik3-fp4-mi355x-vllm-agentic-mtp:
       - { tp: 8, kv-offloading: none, conc-list: [1, 4, 8] , spec-decoding: mtp}
       - { tp: 8, ep: 1, kv-offloading: dram, kv-offload-backend: { name: vllm-simple }, conc-list: [10], spec-decoding: mtp }
 
+# LMCache MP-server DRAM offload on top of the same DSpark MTP serving stack as
+# kimik3-fp4-mi355x-vllm-agentic-mtp (same image, script, and topology). A
+# dedicated key so LMCache points can be selected and swept without re-running
+# the resident and vllm-simple arms of the base key.
+kimik3-fp4-mi355x-vllm-agentic-mtp-lmcache:
+  image: vllm/vllm-openai-rocm:nightly-cb8104839c141609d99f1254459ef3a4f1bd4263
+  model: moonshotai/Kimi-K3
+  model-prefix: kimik3
+  runner: cluster:mi355x-amds
+  precision: fp4
+  framework: vllm
+  multinode: false
+  scenarios:
+    agentic-coding:
+    # 0.50 matches the base key: the LMCache server runs with --shm-name ""
+    # so its L1 lives in regular process memory instead of /dev/shm, and the
+    # budget is no longer capped by the ~1.5 TB shm mount (which forced 0.40
+    # before, run 31644286169).
+    - dram-utilization: 0.50
+      search-space:
+      - { tp: 8, ep: 1, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "0.5.4rc2" }, conc-list: [4, 8, 10, 12], spec-decoding: mtp }
+
 dsr1-fp4-mi355x-sglang-disagg:
   image: lmsysorg/sglang-rocm:v0.5.12-rocm720-mi35x-20260519
   model: amd/DeepSeek-R1-0528-MXFP4-v2

perf-changelog.yaml

@@ -5918,3 +5918,12 @@
     - "Add a TEP2 arm (tp 2, ep 2) to the qwen3.5-fp4-b200-sglang-mtp 8k/1k sweep at concurrency 16, 32, and 64"
     - "Rides on the NVFP4-V2 checkpoint switch from #2205"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2550
+
+- config-keys:
+    - kimik3-fp4-mi355x-vllm-agentic-mtp-lmcache
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Add a dedicated LMCache 0.5.4rc2 DRAM KV-offload key at TP8 conc 4/8/16 on top of the unchanged kimik3-fp4-mi355x-vllm-agentic-mtp DSpark MTP stack, with the version pinned in the master config and consumed by the script via KV_OFFLOAD_BACKEND_METADATA."
+    - "Run one LMCache MP server per node with chunk size 3072 (the minimum multiple of the hybrid KDA/MLA group block sizes) and --separate-object-groups, keeping the L1 in process memory (--shm-name \"\") so the DRAM budget is not capped by /dev/shm."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2583