Open source #Open models Nov 22, 2026 · Originally published Nov 19

NVIDIA open-sources frontend-crates, the Rust tool-call parsers behind Dynamo, with a conformance corpus shared across model families so AI agents can write parsers for new models

When you self-host open models, truncated tool calls and markup leaking into answers are common failures. How these parsers handle bad input, and the agent-driven workflow for adding a parser for a new model.

Image: NVIDIA Technical Blog
Primary source NVIDIA Technical Blog · developer.nvidia.com Read the original ↗

// Key points

  • The parsers turn model output, as token IDs or decoded text, into visible text, reasoning and tool-call events, handling malformed, incomplete and streaming input by documented recovery rules rather than guessing intent, and without leaking model-specific markup.
  • A shared conformance corpus pairs model-specific inputs with expected GOLDEN outputs, so UNIFIED.* cases can be reused across model families including Beam, GPT-OSS, Muse Spark and Nemotron 3.
  • To add a parser, you adapt a GOLDEN test set from the UNIFIED.* cases, implement the parser against the model's grammar and validate with the local conformance report; the repository ships a tool-parser-generator skill for agents.
  • Guided decoding constrains generation to the model's markers and argument schema to reduce malformed calls, but truncation and semantic errors still need the parser's recovery checks.

Builder's takeAnyone self-hosting open models has probably hit half-parsed tool calls, and the cross-model test corpus is worth more than the parsers themselves. Before switching to a new open model, I'd run cases like UNIFIED.* through my own serving stack's tool-call parsing, especially streaming and truncation, before comparing quality.

// Background · from #Open models

Full timeline →
  1. Nov 22 AWS ships a distributed KV caching agent skill: evaluate and set up a shared ElastiCache KV tier from your coding agent, cutting self-hosted inference cost by up to 40% and time to first token by up to 80%
  2. Nov 22 SageMaker JumpStart adds a model leaderboard: more than 70 LLMs compared on quality under one evaluation setup, plus measured time to first token, throughput and instance cost
  3. Nov 22 NVIDIA brings Dynamo into RL training: KV-aware routing and delta weight updates cut H Company's average training-step time by up to 20% and GPU-hours by up to 5%

Every Monday, the week in AI in one email

Every Monday morning: the 6 AI stories that mattered most in the past seven days, with my take, in your inbox.

Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link. See the latest issue →