MLOps2023
Centralizes logs, metrics, traces, frontend RUM and LLM observability into one self-hostable platform, using Parquet + S3-native storage and SQL/PromQL querying to reduce long‑term storage costs and unify telemetry analysis.
AI Client2023
Visual canvas for composing, testing, and deploying LLM-based pipelines and multi-agent workflows. Supports major LLMs and vector databases, exports flows as APIs or MCP servers, and offers a desktop bundle for local experimentation and iteration.
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 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 Agent2023
Enterprise-grade multi-agent orchestration framework that builds, runs, and scales autonomous agent swarms for production. Offers modular swarm architectures, protocol support (MCP, AOP), a marketplace, multi-model provider integrations and observability.
AI Deploy2023
Compresses, deploys, and serves LLMs via two engines: TurboMind for raw speed, a PyTorch engine for flexibility. Claims ~1.8x vLLM throughput through persistent batching, blocked KV cache, and split-and-fuse; ships 4-bit AWQ and KV-cache quantization.
Chatbot2024
Creates personalized digital avatars (AI twins) by fine-tuning LLMs on users' chat history and binding them to chatbots. Provides an end-to-end pipeline — chat export, preprocessing with privacy filters, SFT/LoRA training, and deployment (Telegram/Discord/Slack). Best with larger models and substantial chat data.
AI Deploy2024
GPU kernel library for LLM inference attention, sampling, and KV-cache, built on block-sparse formats with JIT-compiled customizable templates. Reports 29-69% inter-token-latency cuts vs compiler backends; powers SGLang, vLLM, and MLC-Engine.
Hands-on coding tutorial series for large language models with slides and runnable notebooks covering fine-tuning, prompting, RLHF, safety, steganography, watermarking, multimodal models, GUI agents, and deployment. Community-maintained, free course materials for students and researchers.
AI API2024
Build AI workflows once and run them across model providers — GoogleAI, OpenAI, Claude, Ollama — through one SDK. Composable primitives for RAG, tool use, and agents, plus a local dev UI for tracing and debugging, with SDKs in JS/TS, Go, and Python.
AI Infra2024
Disaggregated LLM serving architecture that splits prefill and decode into separate clusters and pools spare CPU, DRAM, and SSD into a distributed KVCache. Powers Kimi in production, handling 75% more requests under the same SLOs.
Embodied AI2024
GPU‑accelerated framework for training physically simulated humanoid characters and robots using reinforcement learning and motion imitation. Provides a modular multi‑backend simulator stack, large‑scale multi‑GPU training recipes, built‑in motion retargeting and an ONNX deployment pathway to real robots.