Results for “megatron-core”

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Guides testing Megatron-LM: test layout, recipe YAML, adding and running unit/functional tests, golden values, marker filters, and CI parity.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Enables Megatron Fully Sharded Data Parallel in Megatron-Bridge with configuration overrides, code anchors, pitfalls, and verification steps.

Launch distributed Megatron-LM training jobs on a SLURM cluster with a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules, container conventions, monitoring, and per-rank failure diagnosis.

Reduces peak GPU memory in Megatron Bridge training by applying expandable segments, parallelism resizing, activation recompute, and CPU offloading constraints.

Configure and validate CPU offloading for Megatron Bridge training, including activation offloading and optimizer state offloading with HybridDeviceOptimizer.

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

Lint and format Python code for Megatron-LM using ruff, black, isort, pylint, and mypy, with commands for autoformatting and import ordering.

Indexes Megatron Bridge recipes and recommends the best starting config based on model, GPU count, and training goal.

Plan, configure, and chain Nemotron model customization steps into single-step or multi-step pipelines for curation, translation, fine-tuning, RL alignment, benchmarking, checkpoint conversion, optimization, and evaluation.

Selects Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes based on Orin SM 8.7 vs Thor SM 11.0 and JetPack version.

Generates kernel-DT overlay fragments to enable 25G/10G/1G MGBE QSFP interfaces on Jetson Thor, verifying pinmux and integrating with the BSP customization workflow.

Bitcoin Core JSON-RPC interface: authentication (cookie, rpcauth), wallet vs node RPCs, common verbs (getblockchaininfo, getrawtransaction, scantxoutset, importdescriptors, walletprocesspsbt, submitpackage, testmempoolaccept), error handling. USE WHEN: scripting bitcoind, integrating a service, debugging RPC errors.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace, covering architectures, routing, load balancing, and expert parallelism.

Develop firmware for microcontrollers, implement RTOS applications, and optimize power consumption for resource-constrained devices.

Developing for multicore systems in Zephyr RTOS. Covers Symmetric Multiprocessing (SMP), Asymmetric Multiprocessing (AMP) with OpenAMP/RPMsg, inter-processor communication (IPC) patterns, and Linkable Extensions (LLEXT). Trigger when designing for SoCs with multiple homogeneous or heterogeneous cores.

Nemotron-4 340B Technical Report

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data, covering correlation testing, available recipes, and multi-GPU examples.

Validate and configure packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs with correct context parallelism constraints.

Investigate a failing GitHub Actions job, extract the root cause, and file a well-structured bug issue against NVIDIA/Megatron-LM.

Plan, debug, tune, evaluate, export, or deploy public Nemotron embedding and reranking retrieval recipes using the current checkout.

Generates custom safety policies for NVIDIA Nemotron content-safety guardrails, producing a Markdown policy, JSON taxonomy, and inference prompts from rough user input.

Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI.

Lock, cap, or customize CPU, GPU, and EMC clock behavior on NVIDIA Jetson devices by editing BPMP DTB and nvpower.sh before flashing.

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

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

Optimizes MoE expert-parallel communication overlap in Megatron Bridge, covering dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.

Post-train LLMs with reinforcement learning using the slime framework, which integrates Megatron-LM for training and SGLang for rollout generation.

HTTP middleware, JWT authentication, auth middleware, custom guards, JWT guard, route middleware, request filter, middleware group, Acorn middleware, guard, rate limiting, CORS, CheckRole, throttle, bearer token, request filtering, middleware registration, HTTP Kernel — using Acorn's Laravel middleware stack inside WordPress/Sage/Bedrock

Scans top 24-hour token movers across major chains via GeckoTerminal, applies pump-risk filters, and outputs a chain leaderboard with per-chain top 5 runners.

Agent C3 - Mixed Methods Design Consultant Comprehensive mixed methods research design specialist covering sequential, concurrent, embedded, and multiphase designs with Morse notation. Core Capabilities: - Sequential Explanatory (QUAN → qual): Explain quantitative results - Sequential Exploratory (QUAL → quan): Develop instruments - Convergent Parallel (QUAN + QUAL): Comprehensive understanding - Embedded (QUAN(qual)): Secondary strand addresses different question - Multiphase: Long-term projects with iterative phases - Morse notation interpretation and recommendation