# ML Deployment & Inference Optimization Tools

> LiteRT, ONNX Runtime and Flower are mentioned most often in AI answers about ML Deployment & Inference Optimization Tools.

HTML: https://parse.gl/markets/ml-deployment-inference-optimization-tools · Site index: https://parse.gl/llms.txt

Window: Since Jul 5

## Brands AI mentions

| Rank | Brand | Mentioned in |
| --- | --- | --- |
| #1 | LiteRT | 38% |
| #2 | ONNX Runtime | 29% |
| #2 | Flower | 26% |
| #4 | llama.cpp | 24% |
| #4 | FedML | 22% |
| #4 | TensorFlow Federated | 20% |
| #4 | PyTorch | 20% |
| #4 | ExecuTorch | 19% |
| #9 | TensorFlow.js | 16% |
| #9 | Transformers.js | 15% |
| #9 | Google Gemini | 15% |
| #9 | bitsandbytes | 14% |
| #9 | JAX | 14% |
| #14 | MediaPipe | 12% |
| #14 | WebLLM | 11% |
| #14 | NVFlare | 11% |
| #14 | Keras | 10% |
| #14 | Apache TVM | 9% |
| #14 | Core ML | 9% |
| #20 | OpenFL | 8% |
| #20 | GGUF | 8% |
| #20 | PyTorch TorchAO | 7% |
| #20 | PySyft | 7% |
| #20 | CMSIS-NN | 7% |
| #20 | vLLM | 6% |
| #20 | GPTQ | 6% |
| #20 | Edge Impulse | 6% |
| #20 | Hugging Face | 5% |
| #20 | AutoAWQ | 5% |
| #20 | TorchVision | 5% |
| #31 | LLM Compressor | 5% |
| #31 | Google AI Edge | 5% |
| #31 | TensorRT-LLM | 5% |
| #31 | GPTQModel | 5% |
| #31 | Gemma | 5% |
| #31 | TensorFlow Serving | 5% |
| #31 | Openmined | 5% |
| #31 | NVIDIA TensorRT | 5% |
| #31 | MLC LLM | 4% |
| #31 | ONNX | 4% |
| #31 | Hugging Face Trainer API | 3% |
| #31 | Gemini | 3% |
| #31 | MLX | 3% |
| #31 | Arm | 3% |
| #31 | Federated AI Technology Enabler | 3% |
| #31 | LangChain LangGraph | 3% |
| #31 | Ollama | 3% |
| #31 | Meta AI | 3% |
| #49 | Google Agent Development Kit (ADK) | 3% |
| #49 | AWQ | 3% |
| #49 | FATE | 3% |
| #49 | uTensor | 3% |
| #49 | SQLite | 3% |
| #49 | MLC AI | 2% |
| #49 | TinyEngine | 2% |
| #49 | LangChain | 2% |
| #49 | Qwen | 2% |
| #49 | NCNN | 2% |
| #49 | timm | 2% |
| #49 | React Native | 2% |
| #49 | DeepMind Gemma | 2% |
| #49 | Microsoft Phi | 2% |
| #49 | Flax | 2% |
| #49 | Google Gemini API | 2% |
| #49 | ML Kit | 2% |
| #49 | Apple Foundation Models | 2% |
| #49 | FedKit | 2% |
| #49 | CrewAI | 2% |
| #49 | AutoRound | 2% |
| #49 | SAP AI Core | 2% |
| #49 | Flutter | 2% |
| #49 | EfficientNet | 2% |
| #49 | Kotlin Multiplatform | 1% |
| #49 | agent-device | 1% |
| #49 | Apple | 1% |
| #49 | FedScale | 1% |
| #49 | Hugging Face Optimum | 1% |
| #49 | MNN | 1% |
| #49 | Hugging Face Hub | 1% |
| #49 | MobFedLS | 1% |
| #49 | MCUNet | 1% |
| #49 | KotlinSyft | 1% |
| #49 | ml5.js | 1% |
| #49 | Agno | 1% |
| #49 | LM Studio | 1% |
| #49 | SwiftSyft | 1% |
| #49 | Pydantic AI | 1% |
| #49 | Google | 1% |
| #49 | PalmClaw | 1% |
| #49 | TorchServe | 1% |
| #49 | HQQ | 1% |
| #49 | Opacus | 1% |
| #49 | TensorFlow Extended (TFX) | 1% |
| #49 | TensorFlow Privacy | 1% |
| #95 | SmolAgents | 1% |
| #95 | NVIDIA ModelOpt | 1% |
| #95 | GGML | 1% |
| #95 | Intel | 1% |
| #95 | KerasCV | 1% |
| #95 | MMDetection | 1% |

## For agents

```text
Ask about this market: POST https://agent.parse.gl/v1/tools/query_metrics   {"measures": ["share_named"], "by": ["brand"], "filter": {"market": ["mkt_159d73a4-7f54-459f-9800-f3f896458cce"]}}
Search the index:      GET  https://parse.gl/api/public/search?q=<words>

No account: what this page shows, 5 example rows a list, about 120 brands a day per address.
Free account: $5 of credit, your own brand in full, a weekly check.
With credit: every row, history, and live checks at $0.01 each. Top up from $5.
Full text of a public answer: 25 a day free, then $0.005 each.
An agent can start a workspace with no account: POST https://agent.parse.gl/v1/workspaces

Connect an assistant: https://agent.parse.gl/mcp
Prices: https://parse.gl/pricing.md    Map of the site: https://parse.gl/llms.txt
```
