Llmtop – Htop for LLM Inference Clusters (vLLM, SGLang, Ollama, llama)
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…
What it does
In the maker’s words, at launch
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 InfraWhisperer/tap/llmtop Or go install github.com/InfraWhisperer/llmtop/cmd/llmtop@latest. ``` Single binary, no Prometheus server needed, no Grafana, no config. Just run llmtop and it auto-discovers local workers. Written in Go with Bubbletea. Working on Kubernetes pod auto-discovery and a GPU metrics view next.
Does the same job
all alternatives →- TVTiny-vLLM – high performance LLM inference engine in C++ and CUDAMay 2026 · github.com · ▲205
- CLCuts Long Horizon Inference Costs by 50% via external KV Cache OffloadJul 2026 · github.com · ▲22
Hey HN, we’re the developers of OpenLake, an open source storage engine for offloading LLM KV caches from GPU memory into a shared tier of RAM and NVMe. We built OpenLake because KV caches are outgrowing GPU memory. A single 256K token conversation on Gemma 4 31B produces approximately 43GB of KV state, more than half the memory of an 80GB H100. The problem becomes even harder across a cluster: a prefix cached on one GPU host is unavailable when the next request lands on a different GPU, forcing the new GPU to repeat work the fleet has already completed. Once the KV cache is offloaded,…
- CRChainFactory – Run Structured LLM Inference with Easy Parallelism2024 · github.com · ▲8
hi everyone. how does moving llm call prompts and output structure definitions away from code into configuration land sound? would you use something like this if it was stable and well documented enough? please don't hold back the criticism. i appreciate all feedback (constructive & otherwise).
Free Inference Engineer and Model Training Roadmap13d ago · inferquest.org · ▲16Free, gamified roadmaps for LLM engineering: an Inference Engineering path (KV caches, CUDA kernels, production vLLM serving) and a Model Training path (pretraining on a budget, scaling laws, SFT/DPO/GRPO) — 185 tasks with auto-verified milestones instead of a paper certificate.
- LTLLGTRT: TensorRT-LLM+Rust server w/ OpenAI-compat and Structured Output2024 · github.com · ▲6
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…
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 · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
