Data
Sglang
Fast structured generation and serving for LLMs with RadixAttention prefix caching.
by Orchestra Research
Search the catalog, filter by category, and install from inside your AI.
Fast structured generation and serving for LLMs with RadixAttention prefix caching.
Builds conversion funnels from raw event data with drop-off attribution, segment comparison, and significance testing, and delivers a filled funnel table with a diagnosed bottleneck and next action.
Design and automate surveys, benchmarks, and data collection to create unique competitive advantages through original research.
Designs presentation tables that read correctly at a glance – numeric alignment, consistent precision, deliberate sort order, unit-labeled headers, and well-placed totals – and delivers a before/after redesign of the reader's table.
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.
Produces a rigorous, honest evaluation report for an ML model – real baselines, business-matched metrics with confidence intervals, slice-level error analysis, calibration checks, and a go/no-go recommendation.
Multi-agent orchestration framework for autonomous AI collaboration.
Apply prioritized PostgreSQL query, connection, schema, concurrency, RLS, access, and monitoring practices.
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models.
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware.
Checks CSV, JSON, and database exports for schema, completeness, consistency, uniqueness, and business-rule violations.
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution.