orchestra-re
94 skills with substantive source documentation and an official publisher or observed installation demand. Read each skill’s original documentation through its card.
orchestra-researchmlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchmodal-serverless-gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchmodel-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchnanogpt
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchnnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchopenrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchoptimizing-attention-flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchpeft-fine-tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchphoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchprompt-guard
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchpytorch-lightning
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchpyvene-interventions
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchray-data
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchray-train
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchrwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchserving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchsparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchspeculative-decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchtensorboard
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchtensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchtransformer-lens-interpretability
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
orchestra-researchweights-and-biases
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform
- 導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日