Results for “model-inference”

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

Apply the scGPT single-cell foundation model (Cui 2024) to annotate and embed cells — zero-shot and fine-tuned cell-type annotation, gene/cell embeddings, batch integration, and gene-regulatory / perturbation inference from AnnData. Use when annotating cell types with a pretrained foundation model, generating scGPT embeddings, integrating batches with a transformer, or running zero-shot single-cell inference on an h5ad. For probabilistic latent models (scVI/scANVI) prefer alterlab-scvi-tools; for the standard QC→cluster→UMAP→DE pipeline prefer alterlab-scanpy; for the AnnData data structure itself prefer alterlab-anndata; for protein language models prefer alterlab-esm. Part of the AlterLab Academic Skills suite.

Execute Python code in a safe sandboxed environment with 100+ pre-installed libraries for data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, and automation.

Train, evaluate, export, and run inference for CenterPose models used in 6-DoF object pose estimation with keypoint regression.

Train, evaluate, export, prune, and run inference for PointPillars 3D object detection models from LiDAR point clouds using NVIDIA TAO.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

Routes NVIDIA Nemotron Speech (Riva) NIM tasks for ASR, TTS, and NMT, covering cloud-hosted inference, self-hosted Docker deployment, and custom model builds.

Train, evaluate, export, quantize, and run inference on Mask2Former models for panoptic, instance, and semantic segmentation using NVIDIA TAO.

Trains, evaluates, exports, and runs inference on FoundationStereo models for stereo depth estimation and 3D reconstruction from stereo image pairs.

Deploy and serve AI/ML models on Modal's serverless cloud platform with on-demand GPUs, autoscaling containers, persistent storage, and scheduled jobs.

Train large-scale MoE models with FP8/INT4 low-precision RL, speculative decoding, and train-inference alignment using the miles framework.

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

Use for writing, reviewing, debugging, or testing Python analysis of Bayesian inference results with ArviZ, including 1.x DataTree groups, legacy InferenceData inputs, xarray dimensions and coordinates, conversion, summaries, R-hat/ESS/MCSE diagnostics, posterior predictive checks, PSIS-LOO, Pareto-k, and model comparison. Trigger on chain/draw shape errors, mislabeled groups, flattened samples, missing log likelihood, or misleading diagnostic claims. Do not use to construct or sample PyMC, NumPyro, or Bambi models, for generic plotting, or for deterministic statistics without Bayesian draws.

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.

Provides deep generative models for single-cell omics analysis, including probabilistic batch correction, transfer learning, differential expression, and multi-modal integration.

Run GGUF models locally with llama.cpp, including finding the right file on the Hugging Face Hub, installing, quantizing, serving, and using Python bindings.

Benchmarks inference latency and computational runtime of transformer models and MLX operations across Apple Silicon and NVIDIA GPU backends, with configurable input lengths and batch sizes.

Write, review, debug, or interpret Python statistical models using statsmodels, including formulas, regression, GLM, time series, robust covariance, diagnostics, prediction intervals, and inference.

Create deployment-ready handoff docs: model card, inference contract, and monitoring requirements. Use when: (1) transferring from DS to engineering, (2) defining SLIs/SLOs, (3) documenting retraining triggers. NOT for: directly provisioning cloud infra.

Runs chest X-ray reasoning smoke tests using the NV-Reason-CXR-3B model via local inference or a public Hugging Face Space API.

Trains, evaluates, exports, and runs inference for Siamese-network-based optical inspection models to detect manufacturing defects and quality issues in image pairs.

Quantize large language models to 4-bit using activation-aware weight quantization, achieving ~3x speedup with minimal accuracy loss for deployment on limited GPU memory.

Use for writing, reviewing, debugging, testing, or diagnosing Python Bayesian models built directly with PyMC, including Model, coords/dims, Data, random variables, potentials, posterior sampling, prior/posterior predictive checks, and InferenceData output. Trigger on model geometry, shape errors, divergences, sampler choice, mutable prediction data, and probabilistic validation. Do not use for Bambi formula models, NumPyro/JAX programs, ArviZ-only analysis of existing draws, deterministic optimization, or general statistics without PyMC code.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Train, evaluate, export, quantize, and run inference for a TAO OneFormer model that performs panoptic, instance, and semantic segmentation using task-conditioned queries.

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

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

Detect anomalies in time-series data using the Azure AI Anomaly Detector SDK for Java, with support for univariate and multivariate analysis, model training, and inference.