VLLM / A2DeepSeek-V4-Flash · A2
每种布局独立记录镜像与脚本。先选拓扑，再核对具体的部署条件。
镜像quay.io/ascend/vllm-ascend:v0.21.0rc1
4x A2: 1 prefill (DP=16) spanning nodes 0-1 + 2 standalone decode (DP=8), MooncakeHybridConnector, kv_port 30000/30200/30300 (engine_id 0/2/3). v0.21.0rc1 refresh: migrated speculative method deepseek_mtp -> mtp (enforce_eager: true; decode keeps num_speculative_tokens 2) and dropped dead env toggles (USE_MULTI_BLOCK_POOL, VLLM_ASCEND_ENABLE_FUSED_MC2, USE_MULTI_GROUPS_KV_CACHE). Cross-node prefill topology, A2 memory tuning, and --chat-template preserved.
脚本与说明
来源记录日期 2026-06-27 · 此页面不重新认定硬件验证结果
镜像quay.io/ascend/vllm-ascend:v0.21.0rc1
2x A2 (8 NPU/node) single mixed engine, DP=16 x TP=1 x EP=16 across both nodes. v0.21.0rc1 refresh: migrated speculative method deepseek_mtp -> mtp (enforce_eager: true) and dropped dead env toggles (USE_MULTI_BLOCK_POOL, VLLM_ASCEND_ENABLE_FUSED_MC2, USE_MULTI_GROUPS_KV_CACHE). A2 memory tuning (max-model-len 131072, gpu-mem 0.90) and --chat-template preserved.
脚本与说明
来源记录日期 2026-06-27 · 此页面不重新认定硬件验证结果
镜像quay.io/ascend/vllm-ascend:v0.21.0rc1
>
脚本与说明
来源记录日期 2026-06-27 · 此页面不重新认定硬件验证结果
镜像quay.io/ascend/vllm-ascend:v0.21.0rc1
4x A2: 2 standalone prefill (DP=8) + 2 standalone decode (DP=8), MooncakeHybridConnector, kv_port 30000/30100/30200/30300 (engine_id 0..3). v0.21.0rc1 refresh: migrated speculative method deepseek_mtp -> mtp (enforce_eager: true; decode keeps num_speculative_tokens 2) and dropped dead env toggles (USE_MULTI_BLOCK_POOL, VLLM_ASCEND_ENABLE_FUSED_MC2, USE_MULTI_GROUPS_KV_CACHE). Repo-specific symmetric topology, A2 memory tuning, and --chat-template preserved.
脚本与说明
来源记录日期 2026-06-27 · 此页面不重新认定硬件验证结果