검증 및 제한 사항¶

LMCACHE_CHUNK_SIZE=4096 \
LMCACHE_ENABLE_KV_EVENTS=True \
LMCACHE_EXTRA_CONFIG='{
  "storage_plugin.RDSBackend.module_path": "lmcache_rbln.storage_plugin.rds_backend",
  "storage_plugin.RDSBackend.class_name": "RDSBackend"
}' \
LMCACHE_LOCAL_CPU=False \
LMCACHE_MAX_LOCAL_CPU_SIZE=0 \
LMCACHE_PRE_CACHING_HASH_ALGORITHM=sha256_cbor_64bit \
LMCACHE_STORAGE_PLUGINS=RDSBackend \
PYTHONHASHSEED=42 \
VLLM_ENGINE_READY_TIMEOUT_S=9600 \
VLLM_NIXL_SIDE_CHANNEL_HOST='<POD_IP>' \
VLLM_NIXL_SIDE_CHANNEL_PORT=5559 \
vllm serve MiniMaxAI/MiniMax-M2.7 \
    --block-size 4096 \
    --enable-auto-tool-choice \
    --gpu-memory-utilization 0.8 \
    --kv-cache-dtype fp8 \
    --kv-events-config '{
      "enable_kv_cache_events": true,
      "publisher": "zmq",
      "endpoint": "tcp://<EPP_HOST>:5557",
      "topic": "kv@<POD_IP>:8000@MiniMaxAI/MiniMax-M2.7"
    }' \
    --kv-transfer-config '{
      "kv_connector": "MultiConnector",
      "kv_role": "kv_both",
      "kv_connector_extra_config": {
        "connectors": [
          {
            "kv_connector": "RblnNixlConnector",
            "kv_role": "kv_both",
            "kv_buffer_device": "rbln",
            "kv_connector_extra_config": {
              "name": "nixl"
            }
          },
          {
            "kv_connector": "RBLNLMCacheConnectorV1",
            "kv_connector_module_path": "lmcache_rbln.integration.vllm.connector",
            "kv_role": "kv_both",
            "kv_connector_extra_config": {
              "name": "lmcache"
            }
          }
        ]
      }
    }' \
    --max-model-len 204800 \
    --max-num-batched-tokens 512 \
    --max-num-seqs 4 \
    --model-impl vllm \
    --pipeline-parallel-size 4 \
    --port 8000 \
    --prefix-caching-hash-algo sha256_cbor \
    --reasoning-parser minimax_m2 \
    --safetensors-load-strategy prefetch \
    --speculative-config '{
      "method": "eagle3",
      "model": "asherszhang/MiniMax-M2.7-EAGLE3-draft-vocab200k",
      "num_speculative_tokens": 3
    }' \
    --tool-call-parser minimax_m2 \
    --trust-remote-code

RBLN_VISIBLE_DEVICES=0 \
VLLM_ENGINE_READY_TIMEOUT_S=9600 \
VLLM_NIXL_SIDE_CHANNEL_HOST='<POD_IP>' \
VLLM_NIXL_SIDE_CHANNEL_PORT=5659 \
vllm serve MiniMaxAI/MiniMax-M2.7 \
    --block-size 4096 \
    --data-parallel-address '<POD_IP>' \
    --data-parallel-rank 0 \
    --data-parallel-rpc-port 5555 \
    --data-parallel-size 4 \
    --enable-auto-tool-choice \
    --enable-expert-parallel \
    --kv-cache-dtype fp8 \
    --kv-events-config '{
      "enable_kv_cache_events": true,
      "publisher": "zmq",
      "endpoint": "tcp://<EPP_HOST>:5557",
      "topic": "kv@<POD_IP>:8200@MiniMaxAI/MiniMax-M2.7"
    }' \
    --kv-transfer-config '{
      "kv_connector": "RblnNixlConnector",
      "kv_role": "kv_both",
      "kv_buffer_device": "rbln",
      "kv_connector_extra_config": {
        "name": "nixl"
      }
    }' \
    --max-model-len 204800 \
    --max-num-batched-tokens 512 \
    --max-num-seqs 4 \
    --model-impl vllm \
    --port 8200 \
    --prefix-caching-hash-algo sha256_cbor \
    --reasoning-parser minimax_m2 \
    --safetensors-load-strategy prefetch \
    --speculative-config '{
      "method": "eagle3",
      "model": "asherszhang/MiniMax-M2.7-EAGLE3-draft-vocab200k",
      "num_speculative_tokens": 3
    }' \
    --tool-call-parser minimax_m2 \
    --trust-remote-code

export GATEWAY=http://<gateway>:80
export OUT=<output-dir>

python -m lm_eval --model local-chat-completions \
  --model_args "base_url=${GATEWAY}/v1/chat/completions,model=MiniMaxAI/MiniMax-M2.7,num_concurrent=16,timeout=6000" \
  --tasks gsm8k \
  --apply_chat_template --fewshot_as_multiturn true \
  --gen_kwargs max_gen_toks=65536,seed=None,temperature=1.0,top_p=0.95 \
  --output_path "${OUT}"

python -m lm_eval --model local-chat-completions \
  --model_args "base_url=${GATEWAY}/v1/chat/completions,model=MiniMaxAI/MiniMax-M2.7,num_concurrent=16,timeout=6000" \
  --tasks mmlu_pro --limit 20 \
  --apply_chat_template --fewshot_as_multiturn true \
  --gen_kwargs max_gen_toks=65536,seed=None,temperature=1.0,top_p=0.95 \
  --output_path "${OUT}"