LLGTRT: TensorRT-LLM+Rust server w/ OpenAI-compat and Structured Output
I wanted to share a project I've been working on for the past few weeks: llgtrt. It's a Rust implementation of a HTTP REST server for hosting Large Language Models using llguidance library for constrained output with NVIDIA TensorRT-LLM. The server is compatible with the OpenAI REST API and supports structured JSON schema enforcement as well as full context-free grammars (via Guidance). It's similar in spirit to the Python-based TensorRT-LLM OpenAI server example but written entirely in Rust and built with constraints in mind. No Triton Inference Server involved. This also serves as a demo…
What it does
In the maker’s words, at launch
I wanted to share a project I've been working on for the past few weeks: llgtrt. It's a Rust implementation of a HTTP REST server for hosting Large Language Models using llguidance library for constrained output with NVIDIA TensorRT-LLM. The server is compatible with the OpenAI REST API and supports structured JSON schema enforcement as well as full context-free grammars (via Guidance). It's similar in spirit to the Python-based TensorRT-LLM OpenAI server example but written entirely in Rust and built with constraints in mind. No Triton Inference Server involved. This also serves as a demo for the llguidance library, which lets you apply sampling constraints via Rust, C, or Python interface, with minimal generation overhead and no startup cost. Any feedback or questions are welcome!
Does the same job
all alternatives →
- OBOfferyn – Build Tools for LLMs in Rust, with Model Context Protocol2025 · github.com · ▲7
- IEI embedded 685M public texts in 32 minutes (on 8x A100, Rust, TensorRT)Jun 2026 · github.com · ▲7
Quick note on how it works and how I've done my batch embedding engine IgniteMS. The whole thing runs as one process using Rust, reading input, tokenizing, packing batches, keeping the queue full. TensorRT handles inference. Python is only as a wrapper. I built it this way because when you use more than couple of GPUs, the GPUs stop being the problem. CPU cannot feed them fast enough. One A100 can go through batches faster than Python can tokenize and feed, so the GPU just sits there idle waiting for work. Most of my time went into optimizing this. At 8 GPUs that was basically the entire…
- LHLlmtop – Htop for LLM Inference Clusters (vLLM, SGLang, Ollama, llama)Mar 2026 · github.com · ▲5
I work on inference scheduling — KV cache-aware routing, load balancing across GPU workers, that kind of thing. I wanted something like k9s but for my inference stack. Nothing existed, so I built it. llmtop is a real-time terminal dashboard for LLM inference workers. It scrapes the Prometheus /metrics endpoints that vLLM, SGLang, and LMCache already expose and shows everything in one view: KV cache usage, queue depth, TTFT/ITL latencies (P50/P99 from histogram buckets), token throughput, prefix cache hit rates. Color-coded — red means go fix it. ``` brew install…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, October 2024
the whole month →
Softr for Notion▲925Turn Notion databases into portals & apps with no code
Dev tools · 2024 · softr.io
One inbox for all your work discussions
Work · 2024 · generalcollaboration.com