AI Audio2022
Alibaba DAMO Academy, Northwestern Polytechnical University (NWPU) +5Alibaba DAMO Academy, ModelScope
Bundles ASR, voice activity detection, punctuation, and speaker diarization into one pipeline, with pretrained models like Paraformer and SenseVoice. SenseVoice runs ~17x realtime on CPU; also ships streaming ASR and an OpenAI-compatible API.
Chatbot2022
Connects one LLM agent to 15+ chat platforms — QQ, WeChat Work, Feishu, Telegram, Discord, Slack — from a single self-hosted backend. Routes to OpenAI, Anthropic, Gemini, DeepSeek or Ollama, and adds a WebUI, MCP tools, and a 1000+ plugin marketplace.
AI Train2023
Modular PyTorch-based framework for building, training, and deploying physics-informed ML models (neural operators, PINNs, GNNs, diffusion). Provides GPU‑optimized training, domain-specific datapipes for meshes/point clouds, distributed scaling and a model zoo.
AI API2023
Routes one API call across hundreds of LLMs from dozens of providers, with credits, fallbacks, pricing comparison, and data-policy controls for teams that need model choice without wiring every provider separately.
AI Infra2023
Aggregates alerts from dozens of monitoring tools into a single pane of glass, then deduplicates, correlates, and enriches them. Automates incident response with declarative YAML workflows — like GitHub Actions for your monitoring stack.
AI Deploy2023
Open-source LLM inference and serving engine built around PagedAttention, which manages the KV cache like OS virtual memory to cut waste and raise throughput. Supports continuous batching, KV cache sharing, quantization, and an OpenAI-compatible API.
AI Infra2023
Runs AI-generated code in secure, isolated cloud sandboxes you control via Python or JavaScript SDKs; supports self-hosting (Terraform) and AWS/GCP, enabling agents and code-interpreting workflows to execute real-world tools safely.
AI Infra2023
Runs large language models entirely in C/C++ with no external dependencies, using 1.5-to-8-bit integer quantization and CPU+GPU hybrid inference to fit models larger than available VRAM. Backs Ollama, LM Studio, and most local-inference tooling.
AI Infra2023
Puts OpenAI-, Anthropic- and Ollama-compatible endpoints in front of 60+ inference backends, so existing client code runs unchanged against local models for text, vision, audio, image and embeddings. Runs CPU-only or accelerated, data stays local.
AI API2023
Self-hosted gateway putting OpenAI, Claude, Gemini, DeepSeek and 20+ providers behind one OpenAI-compatible endpoint. Adds per-token quotas, channel load balancing and usage billing, so teams or resellers meter keys without sharing upstream credentials.
AI Deploy2023
Compiles one LLM into device-native binaries running on CUDA, ROCm, Metal, Vulkan, WebGPU, and CPU — same model from server to browser to phone. On Apache TVM, it ships MLCEngine with an OpenAI-compatible API across Python, JS, REST, iOS, and Android.
AI Infra2023
Runs 70B-class LLM inference on a single 4GB GPU without quantization and supports Llama3.1 405B on 8GB VRAM. Uses layer-splitting and block-wise model compression (4/8-bit) to reduce disk load and can speed up inference loading by up to ~3x; integrates with Hugging Face models.