diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml index c5d5edac68..33d6a3f34b 100644 --- a/configs/nvidia-master.yaml +++ b/configs/nvidia-master.yaml @@ -1393,7 +1393,7 @@ kimik3-fp4-b300-vllm-agentic-dspark: - { tp: 8, ep: 1, dcp-size: 8, spec-decoding: mtp, kv-offloading: dram, kv-offload-backend: { name: mooncake, version: "0.3.11.post1" }, conc-list: [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 70] } dsr1-fp8-b200-trt: - image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc14 + image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc27 model: deepseek-ai/DeepSeek-R1-0528 model-prefix: dsr1 runner: cluster:b200-nscale