Results for “moe”

66 skills
nvidia
nemo-mbridge-perf-moe-comm-overlap
Optimizes MoE expert-parallel communication overlap in Megatron Bridge, covering dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.
2.2k · bundle
tianhao909
moe-training
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.
1 · bundle
qcmuu
moe-training
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.
0 · bundle
orchestra-research
moe-training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace, covering architectures, routing, load balancing, and expert parallelism.
10.4k · bundle
orchestra-research
miles-rl-training
Train large-scale MoE models with FP8/INT4 low-precision RL, speculative decoding, and train-inference alignment using the miles framework.
10.4k · bundle
lingxling
pymoo
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.
253 · bundle
More results
nvidia
nemo-mbridge-perf-moe-vlm-training
Provides practical guidance for training Mixture-of-Experts Vision-Language Models in Megatron Bridge, comparing FSDP and 3D-parallel approaches with lessons from recent multimodal experiments.
2.2k · bundle
k-dense-ai
pymoo
Solve single and multi-objective optimization problems using NSGA-II/III, MOEA/D, and other evolutionary algorithms with customizable operators, constraint handling, and benchmark problems.
30.2k · bundle
qhjqhj00
pymoo
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.
3 · bundle
levalencia
pymoo
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.
3 · bundle
thedixitjain
pymoo
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.
2 · bundle
jackychenlu
pymoo
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.
0 · bundle
metinduraktr-44
pymoo
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.
0 · bundle
chen-yu-hao
pymoo
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.
5 · bundle
nvidia
nemo-mbridge-perf-moe-long-context
Provides guidance for training Mixture-of-Experts models with long context windows, covering context parallelism sizing, selective recomputation, dispatcher choices, and practical patterns from recent experiments.
2.2k · bundle
demerzels-lab
moa
Orchestrates three frontier models to debate a question and synthesizes their best insights into a single superior answer.
10 · bundle
johnalbertini14-glitch
moa
Runs a Node.js CLI that sends a question to three frontier LLMs in parallel, then synthesizes their responses into a single answer via an aggregator model, with paid and free tiers.
1 · bundle
artubss
pymoo
Framework de otimização multi-objetivo. NSGA-II, NSGA-III, MOEA/D, frentes de Pareto, tratamento de restrições, benchmarks (ZDT, DTLZ), para problemas de design e otimização em engenharia.
10 · bundle
nvidia
nemo-automodel-model-onboarding
Guides implementation of new model architectures in NeMo AutoModel through five phases: discovery, implementation, registration, validation, and testing.
2.2k · bundle
nvidia
launch-nemo-rl
Launch, monitor, stop, and debug NeMo-RL recipes on a Kubernetes cluster using the nrl-k8s CLI, supporting ephemeral and long-lived RayCluster modes.
2.2k · bundle
nvidia
tao-train-mask-auto-encoder
Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.
2.2k · bundle
nvidia
nemo-rl-session-memory
Maintain durable session memory across agent disconnects by writing structured checkpoints to the repo's session directory, enabling context recovery.
2.2k · bundle
akillness
moli
Drive Moli (`moli`), Lexmount's open-source headless browser for AI agents, built around on-demand rendering: real JavaScript, DOM, and CSS by default, with layout and pixels computed only when explicitly requested via `--layout`. Use when the user wants to fetch/extract a live JavaScript-rendered page as Markdown/HTML/JSON/semantic-tree, capture a screenshot or PDF, run a small bounded crawl, start a CDP/WebDriver automation server for Playwright/Puppeteer, replace a Chromium/ChromeDriver dependency, or diagnose readiness/network/frame issues on a rendered page. Triggers on: "moli fetch", "moli serve", "headless browser for agents", "on-demand rendering browser", "CDP server without Chrome", "structure-first web scraping", "Lexmount browser", "moli-webfetch", "moli-cdp-server".
42 · bundle
sethmblack
bob-hope-expert
Embody the comedic persona of Bob Hope, delivering topical, self-deprecating, and bipartisan humor with impeccable timing and adaptability to any audience.
6
eliferjunior
mojo
Expert guidance for Mojo, the programming language by Modular that combines Python's usability with C-level performance. Helps developers write high-performance AI/ML code, optimize numerical computations with SIMD and parallelism, and gradually port Python code to Mojo for orders-of-magnitude speedups.
0
qcmuu
nemo-curator
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
0 · bundle
demerzels-lab
memos
Provides a simple interface to the Memos API for creating and managing memos.
10 · bundle
demerzels-lab
neo
Load expert mental models on-demand to enhance reasoning, with a library of modules across 15 categories and commands to manage a personal crew.
10 · bundle
sethmblack
bill-maher-expert
Adopts the provocative, contrarian voice of Bill Maher to deliver sharp political and social commentary, using signature techniques like 'New Rule' and 'Both-Sides Skewer'.
6
orchestra-research
nemo-curator
GPU-accelerated data curation for LLM training, supporting text, image, video, and audio with fuzzy deduplication, quality filtering, semantic deduplication, PII redaction, and NSFW detection.
10.4k · bundle
eliferjunior
mobx
You are an expert in MobX, the simple and scalable state management library based on transparent reactive programming. You help developers build React applications with observable state, automatic tracking of dependencies, computed values, actions for state mutations, and reactions for side effects — providing a natural, class-based or functional approach where the UI automatically updates when state changes without manual subscriptions.
0
inskillflow
molykit
CRITICAL: Use for MolyKit AI chat toolkit. Triggers on: BotClient, OpenAI, SSE streaming, AI chat, molykit, PlatformSend, spawn(), ThreadToken, cross-platform async, Chat widget, Messages, PromptInput, Avatar, LLM
1
antigravity
molykit
Build cross-platform AI chat interfaces with Makepad using MolyKit, including async utilities, chat widgets, and OpenAI-compatible client integration.
42.4k
kbarbel640-del
neo
Loads expert mental models on-demand to enhance reasoning, with a library of modules and commands to manage them.
1 · bundle
phoroth
moatmri
Analyzes AI disruption pressure across a business, maps competitive exposure, and produces a 90-day defensive action plan.
3
sandeeprdy1729
moco
Comprehensive guide to moco. Master the concepts, implementation, best practices, and real-world applications of moco in professional environments.
1