Tag
Explore by tags
Provides high-throughput, low-latency GPU communication kernels for Mixture-of-Experts (MoE) and expert-parallel workloads, with NVLink↔RDMA-aware forwarding, FP8/BF16 support, and low-latency RDMA hooks for inference decoding.
Keeps codebases, PDFs, Slack, and docs continuously indexed for RAG and knowledge graphs by recomputing only what changed, not the whole dataset. You declare target state in Python; a Rust engine maintains it with per-row lineage back to the source.
Framework-agnostic library for connecting and optimizing teams of AI agents built in LangChain, LlamaIndex, CrewAI, Semantic Kernel, or Google ADK. Profiles them down to individual tokens, traces execution, and runs built-in evaluation.
Runs and fine-tunes LLMs locally on Apple silicon via the MLX framework, pulling thousands of Hugging Face models with one command. Adds 4- and 8-bit quantization, LoRA and full fine-tuning, prompt caching, and distributed inference across Macs.
Builds, evaluates, and deploys multi-agent systems in Python, code-first. A graph-based runtime handles routing, fan-out/fan-in, loops, retries, and human-in-the-loop; a Task API covers agent-to-agent delegation, plus a CLI and web UI.
Official Go implementation of the Model Context Protocol for building MCP servers and clients. Tool handlers are type-safe, with JSON schemas inferred from Go structs via generics. Ships stdio, command, streamable-HTTP, SSE, and in-memory transports.
Builds production-grade AI agents and multi-agent workflows in .NET and Python, with graph-based orchestration for sequential, concurrent, and handoff patterns. Unifies Microsoft's Semantic Kernel and AutoGen lineages, adding durable, checkpointed runs.
Converts PDFs into AI-ready structured outputs (Markdown, JSON with bounding boxes, HTML) for RAG and accessibility workflows; offers deterministic local parsing plus a hybrid AI mode for complex tables, OCR, formulas, and auto-tagging previews.
Builds production AI agents around a model-driven loop with provider abstraction, tools, guardrails, streaming, MCP, tracing, and multi-agent patterns across Python and TypeScript SDKs.
Reimplements the vLLM inference engine from scratch in ~1,200 lines of readable Python, matching its offline throughput on small models. Prefix caching, tensor parallelism, torch.compile, and CUDA graphs are all kept legible.
A toolkit and open-weights system for real-time streaming music generation — offers two model sizes (230M / 2.4B), a Python inference library (JAX/MLX), and a C++ engine optimized for Apple Silicon for embedding into DAWs and apps; real-time streaming requires M‑series chips.