Results for “dynamo”

Validates that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after deploying a disagg or multi-node recipe to confirm KV transport is correct, or use troubleshoot for already-failed pods.

Build synthetic datasets and data generation pipelines using the Data Designer library.

Navigate the PhysicsNeMo repository by discovering model families, datapipes, and examples through live file search, without writing training code.

Train, evaluate, export, distill, quantize, or run inference for a TAO DINO 2D object detector using transformer-based detection with denoising training and multi-scale features.

Trains, evaluates, exports, quantizes, and runs inference for a Mask Grounding DINO model for open-set instance segmentation guided by text prompts.

Master Django 5.x with async views, DRF, Celery, and Django Channels. Build scalable web applications with proper architecture, testing, and deployment. Use PROACTIVELY for Django development, ORM optimization, or complex Django patterns.

Solves single- and multi-objective optimization problems with NSGA-II/III, MOEA/D, and other evolutionary algorithms, including constraint handling, Pareto front analysis, and benchmark problems.

Trains LLMs with SimPO, a reference-free preference optimization method that outperforms DPO, using configurable hyperparameters and workflows for various models and tasks.

Train language models with SimPO, a reference-free preference optimization method that outperforms DPO without needing a reference model.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Provides expert guidance for distributed training with DeepSpeed, covering ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, and sparse attention.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Configure fault tolerance, straggler detection, preemption, in-process restart, and re-run state machine for Megatron Bridge training jobs.

Trains, evaluates, exports, quantizes, and runs inference for a Grounding DINO model that detects objects described by text prompts without a fixed class vocabulary.

Solve single- and multi-objective optimization problems with NSGA-II/III, MOEA/D, and other evolutionary algorithms, including Pareto front analysis, constraint handling, and benchmarking on standard test problems.

Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for the user's actual intent — single still vs video, full character vs face only, dialog scene vs silent motion. Triggers on "face swap", "swap face", "deepfake", "face replacement", "character swap", "head swap", "put X's face on Y", "make this video star X", "replace the actor in this video", "swap the character in the photo", "deepfake video", "ReActor alternative", or any explicit ask to substitute one identity for another.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Proposes exactly one personal side-project idea per invocation, sized to a 1-3 day MVP. Targets CLI, automation, LLM, DX, productivity, and data-viz angles; avoids clichés like TODO apps, weather apps, and pomodoro timers. Output is an 8-section brief including a ready-to-paste coding-agent prompt. Use for morning/daily idea rituals and weekend-hack ideation. Don't use for existing-product feature proposals (Spark), dialogue brainstorming (Riff), or prototype implementation (Forge).

Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for the user's actual intent — single still vs video, full character vs face only, dialog scene vs silent motion. Triggers on "face swap", "swap face", "deepfake", "face replacement", "character swap", "head swap", "put X's face on Y", "make this video star X", "replace the actor in this video", "swap the character in the photo", "deepfake video", "ReActor alternative", or any explicit ask to substitute one identity for another.

Pythonic wrapper around RDKit for cheminformatics, simplifying SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, and parallel processing while returning native rdkit.Chem.Mol objects.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Route goalflow (wanmol/goal-flow) work — a LangGraph framework that combines workflow graphs with agent loops — into exactly one mode: fit check, transpiling a Dify DSL export into runnable LangGraph Python, authoring workflow nodes and edges, building an `agent_kit` loop with middleware and a harness, wiring the serving layer (data adapters, SSE streaming, HITL, Redis/MySQL, API-key registration), or running the pre-publish security gate. Use when the user wants Dify's visual design without Dify's runtime, a graph node that hosts an agent loop, an OpenAI-compatible wire protocol over their own workflows, or prompt-injected `SKILL.md` capabilities. Triggers on: goalflow, goal-flow, dify to langgraph, dify transpiler, dify DSL export, BaseWorkflow, agent_kit, AgentBaseNode, DataAdapter, chunk processor, HITL interrupt, dify2langgraph. Route plain graph-API questions to `langgraph-fundamentals` and `langgraph-workflow`.

Expert guidance for distributed NoSQL databases (Cassandra, DynamoDB). Focuses on mental models, query-first modeling, single-table design, and avoiding hot partitions in high-scale systems.

Walks users from a bare AKS cluster to a running AI model deployment, covering cluster verification, controller install, GPU assessment, provider setup, and first deployment.