ai-dynamo

33 mods across 1 repository, 7.9k stars between them.

troubleshoot-dynamo

25

ai-dynamo/dynamo

Skill Claude CodeCodex

Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use deploy-dynamo-recipe or dynamo-router-starter before this for normal bring-up.

7.9k 2d ago C 57 tokens

visual-review

26

ai-dynamo/dynamo

Skill Claude CodeCodex

Create self-contained interactive HTML code-review dashboards from GitHub or GitLab pull requests, checked-out branch diffs, or supplied unified diffs, with correctness and safe-to-merge scores, smell indicators, interactive component and finding diagrams, structured finding packages, per-finding diff tabs with…

7.9k 2d ago A 106 tokens

dynamo AGENTS.md

27

ai-dynamo/dynamo

Instructions file CodexOpenCode

AGENTS.md instructions for ai-dynamo/dynamo, covering dynamo — agent guide, agent instruction files, skills, improving these instructions and optimization role dispatch.

7.9k 2d ago A 3,782 tokens

dynamo CLAUDE.md

28

ai-dynamo/dynamo

Instructions file

Claude Code instructions for ai-dynamo/dynamo, a project described as: A Datacenter Scale Distributed Inference Serving Framework.

7.9k 2d ago A 5 tokens

agent-hints

29

ai-dynamo/dynamo

Agent

Agent hints are optional per-request metadata that a harness sends under nvext.agenthints. Dynamo parses these hints in the frontend and passes them to the router and, where supported, backend runtimes.

7.9k 2d ago A 0 tokens

agent-tracing

30

ai-dynamo/dynamo

Agent

Agent tracing captures request timing, token counts, worker placement, finish metadata, and replay hashes for eligible LLM requests. Requests with session identity also carry agent context, which lets analysis tools group LLM turns and tool activity into the same run.

7.9k 2d ago A 0 tokens

overview

31

ai-dynamo/dynamo

Agent

NVIDIA Dynamo adds agent-aware serving features without taking ownership of the agent loop: your harness still manages prompts, tools, subagents, and reasoning state, while Dynamo uses metadata attached to each LLM request to correlate work, improve routing and scheduling, manage KV cache behavior, and produce traces…

7.9k 2d ago A 0 tokens

priority-scheduling

32

ai-dynamo/dynamo

Agent

Priority scheduling lets a client mark one request as more important than another. Dynamo exposes two related request fields.

7.9k 2d ago A 0 tokens

ai-dynamo/dynamo

Agent

Agent "thunderagent-program-scheduler" from ai-dynamo/dynamo, covering the problem, the scheduler, scheduler tick, tool-boundary pause/resume semantics and program lifetime.

7.9k 2d ago A 0 tokens