diff --git a/docs_new/docs/advanced_features/pd_disaggregation.mdx b/docs_new/docs/advanced_features/pd_disaggregation.mdx index ff92b55db..dc0ef981b 100644 --- a/docs_new/docs/advanced_features/pd_disaggregation.mdx +++ b/docs_new/docs/advanced_features/pd_disaggregation.mdx @@ -36,6 +36,16 @@ For deploying PD disaggregation at scale with load balancing and fault tolerance uv pip install mooncake-transfer-engine ``` +### IB Device Configuration + +`--disaggregation-ib-device` supports the following formats when using the Mooncake backend: + +1. Shared device list for all GPUs: `mlx5_0` or `mlx5_0,mlx5_1` +2. Per-GPU JSON mapping: `{"0": "mlx5_0,mlx5_1", "1": "mlx5_2,mlx5_3"}` +3. Path to a JSON file containing the same per-GPU mapping + +Each JSON value uses the same comma-separated device list format as the shared configuration. + ### Usage ### Llama Single Node diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py index 14c337d6f..0e4b628b4 100644 --- a/python/sglang/srt/server_args.py +++ b/python/sglang/srt/server_args.py @@ -6844,9 +6844,12 @@ class ServerArgs: "--disaggregation-ib-device", type=str, default=ServerArgs.disaggregation_ib_device, - help="The InfiniBand devices for disaggregation transfer, accepts single device (e.g., --disaggregation-ib-device mlx5_0) " - "or multiple comma-separated devices (e.g., --disaggregation-ib-device mlx5_0,mlx5_1). " - "Default is None, which triggers automatic device detection when mooncake backend is enabled.", + help="The InfiniBand devices for disaggregation transfer. Supports a single device " + "(e.g., --disaggregation-ib-device mlx5_0), a shared comma-separated list " + "(e.g., --disaggregation-ib-device mlx5_0,mlx5_1), a per-GPU JSON mapping " + '(e.g., --disaggregation-ib-device \'{"0": "mlx5_0,mlx5_1", "1": "mlx5_2"}\'), ' + "or a path to a JSON file containing that mapping. Default is None, which triggers " + "automatic device detection when mooncake backend is enabled.", ) parser.add_argument( "--disaggregation-decode-enable-radix-cache",