Laguna M.1
serving recipe.

Floors are the minimum the vLLM recipe publishes across the whole replica, from vLLM's own runs. The control plane compares them with its own sizing from the model config.

• Tensor ParallelFits inside one node's interconnect. single_node_tp
• Tensor + Expert ParallelFits inside one node's interconnect. single_node_tep
• Data + Expert ParallelFits inside one node's interconnect. single_node_dep
• Multi-Node Tensor ParallelSpans nodes. multi_node_tp
• Multi-Node Data + Expert ParallelSpans nodes. multi_node_dep
• Multi-Node Tensor + Expert ParallelSpans nodes. multi_node_tep

The recipe does not mark any hardware as verified.

Wingsmith runs models through NVIDIA Dynamo, so it serves on NVIDIA GPUs. Other vendors are listed as the recipe states them.

vllm serve poolside/Laguna-M.1 \
  --enable-auto-tool-choice \
  --tool-call-parser poolside_v1 \
  --reasoning-parser poolside_v1 \
  --default-chat-template-kwargs '{"enable_thinking": true}'

Features

• Tool callingOn by defaultEnable automatic tool choice with Poolside's tool-call parser
• ReasoningOn by defaultEnable interleaved thinking (on by default) with Poolside's reasoning parser

1. Register the weights

   In the console, or through the API. Resolving a slug proposes an artifact and writes nothing.

   curl "http://localhost:8000/v1/artifacts/resolve?source=hf:poolside/Laguna-M.1"

2. Read the draft

   The draft carries this recipe as upstream evidence: the tested flags, the precision and memory floor, the parallelism layouts, and the hardware vLLM verified, with links back to the recipe. Nothing from it is applied without you, and the draft warns when the plane's own sizing and the published floor differ by a quarter or more.

3. Create the workload

   Choose the engine, device shape and scale. The plane picks the clusters, and each cluster's operator renders the deployment as a Dynamo graph.

4. Give it an endpoint

   One model name for clients, routed by the gateway to deployments on every cluster serving it.

Run the control plane locally →

• How much GPU memory does Laguna M.1 need?The vLLM recipe publishes a minimum of 135 GB across the whole replica for its NVFP4 variant; BF16 540 GB, FP8 270 GB. That is vLLM's own measurement, not a per-GPU figure.
• Which parallelism layouts does the Laguna M.1 recipe support?Tensor Parallel, Tensor + Expert Parallel, Data + Expert Parallel, Multi-Node Tensor Parallel, Multi-Node Data + Expert Parallel and Multi-Node Tensor + Expert Parallel.
• Can Wingsmith serve Laguna M.1?Wingsmith serves models through NVIDIA Dynamo on clusters with NVIDIA GPUs. Register poolside/Laguna-M.1 and the plane attaches this vLLM recipe to the draft as evidence: its tested flags, precision and memory floor, for you to review rather than applied on your behalf. The recipe reports no end-to-end run on NVIDIA hardware.

From the vLLM recipe for poolside/Laguna-M.1 ↗ (snapshot at 4bcc189), Apache 2.0.