Tool calling not working with Nemotron-3-Super-120B-A12B-NVFP4 on DGX Spark (SM12.1)

Setup:
∙ DGX Spark (GB10, SM12.1)
∙ vLLM 0.17.2rc1 (pinned — 0.18.x breaks NVFP4 on SM12.1)
∙ --tool-call-parser qwen3_coder
∙ --enable-auto-tool-choice
∙ Open WebUI as frontend
Problem:
Tool calls don’t execute — the model outputs raw JSON instead of a proper function call that vLLM intercepts. Example output:

{ “tool”: “market-prices”, “arguments”: { “symbol”: “AAPL” } }

The model’s own thinking block shows it deciding not to use tools (“we should say we can’t”), suggesting the tool schema isn’t being properly injected or parsed.
What I know:
∙ The tool call fix for qwen3_coder was merged in vLLM 0.18.0 (per the NVIDIA improvements thread)
∙ 0.18.x currently crashes on SM12.1 with MergedColumnParallelLinear has no attribute ‘workspace’
∙ So I’m stuck on 0.17.2rc1 without the fix
Question:
Is there a backport or workaround to get tool calling working on 0.17.2rc1? Or is there a patched 0.18.x build that works on SM12.1?

Have you tried recently?

sparkrun run @spark-arena/55beae02-e7a5-4e8a-98d3-325ba86b4583

Hi digiegg,

Are you still facing this issue?

Did you enable OpenWebUI native tool calling? It is off by default.

Admin Panel → Settings → Models → (Your/Model Name) → Advanced Params → Show → Function Calling → Should say “Native”.

Native fixed it. Sorry forgot to update this. Thanks!