Tag
Explore by tags
Provides a self‑hosted OpenAI‑compatible gateway that exposes one API endpoint to route requests to 40+ model providers, issue revocable virtual keys, enforce budgets before spend, and record usage.
A non-autoregressive, multilingual System‑1 decision model that answers typed questions (choice/score/noul) over text or JSON in a single forward pass with probability distributions. Key differences: calibrated-probability design, sub-35ms GPU latency, and built-in multilingual routing; requires per-workflow recalibration and validation on long or low-resource languages.
Turns a context, a question, and 2–20 candidate answers into a single chosen option for classification, routing, ordered scores, and Boolean decisions. Built on mmBERT-small with a 144.3M-parameter decision head, runs on CPU with up to 8,192 combined tokens; FP32 weights occupy 550.5 MiB and are Apache‑2.0 licensed.
Performs schema-driven, low-latency classification and structured decision-making over English text. Supports multi-head scoring, constrained joint decoding with confidence/feasibility metadata, span extraction, and local CPU/GPU deployment via the gliner2 runtime.
Provides 150,000 source‑grounded decision examples for training models that pick options, judge yes/no propositions, or assign ordered scores. Each row pairs a 'state' with JEV-style typed questions (CHOICE/NOUL/SCORE); multiple configs and train/test splits are included, license mixed/unknown.
Reduces self-attention complexity to O(N log N) by using a coarse-to-fine (pyramid) Top-K block selection with LogSumExp scoring, implemented with hardware-aware Triton kernels for fused routing and scoring—aimed at long-context LMs and retrieval tasks.
A 180,000-row labeled dataset of agent decision steps for training fast decision models that choose whether to call a tool, which tool to pick, and whether arguments are complete. Provides leakage-safe splits, typed questions, canonical state/request fields, and ready-to-use Parquet format for low-latency routers.
Normalizes each domain's teacher feedback spread during multi-teacher on-policy distillation so that no domain (e.g., instruction following) overwhelms others, improving student recovery of specialist skills and raising average scores across benchmarks.
Models sequence generation by unmasking multiple tokens per denoising step and replaces a factorized reverse process with a mixture over discrete routing-based latents from an MoE backbone; improves few-step sampling quality without increasing active parameters.
Proposes a forward-process RL method that dynamically localizes gradient updates and adapts multi-reward coordination for joint audio–video diffusion models. Uses bidirectional cross-attention responses for token/layer routing and preference-preserving reweighting to balance competing objectives, improving modality quality, alignment, and synchronization.
Serves token-level routed LLM inference by dispatching requests to per-model asynchronous subservers and using delayed-batching scheduling to reduce admission latency and step desynchronization. Exposes a request-centric route-send-receive API and reports 2.01–64.15× decoding throughput gains versus single-LLM servers.
Explores asymmetric compute allocation in looped Mixture-of-Experts models by compressing the first loop visit's sequence and reallocating saved compute to enlarge hidden size, yielding consistent NLL reductions and predicted compute savings across 1.3B–7B configurations.