Alternatives
Products that do what Llmtop – Htop for LLM Inference Clusters (vLLM, SGLang, Ollama, llama) does
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…
- 1TV
May 2026 · github.com
- 2KR
I discovered that in LLM inference, keys and values in the KV cache have very different quantization sensitivities. Keys need higher precision than values to maintain quality. I patched llama.cpp to enable different bit-widths for keys vs. values on Apple Silicon. The results are surprising: - K8V4 (8-bit keys, 4-bit values): 59% memory reduction with only 0.86% perplexity loss - K4V8 (4-bit keys, 8-bit values): 59% memory reduction but 6.06% perplexity loss - The configurations use the same number of bits, but K8V4 is 7× better for quality This means you can run LLMs with 2-3× longer…
2025 · github.com
- 3
- 4WM
We wrote our inference engine on Rust, it is faster than llama cpp in all of the use cases. Your feedback is very welcomed. Written from scratch with idea that you can add support of any kernel and platform.
2025 · github.com
- 5AT
I recently built a small open-source tool to benchmark different LLM API endpoints — including OpenAI, Claude, and self-hosted models (like llama.cpp). It runs a configurable number of test requests and reports two key metrics: • First-token latency (ms): How long it takes for the first token to appear • Output speed (tokens/sec): Overall output fluency Demo: https://llmapitest.com/ Code: https://github.com/qjr87/llm-api-test The goal is to provide a simple, visual, and reproducible way to evaluate performance across different LLM providers, including…
2025 · llmapitest.com
- 6LL
Hey, recently I took inspiration from llama.cpp, ollama, and many other similar tools that enable inference of LLMs locally, and I just finished building a Llama inference engine for the 8B model in CUDA C. I recently wanted to explore my newly founded interest in CUDA programming and my passion for machine learning. This project only makes use of the native CUDA runtime api and cuda_fp16. The inference takes place in fp16, so it requires around 17-18GB of VRAM (~16GB for model params and some more for intermediary caches). It doesn’t use cuBLAS or any similar libraries since I wanted to be…
2025 · github.com
- 7CL
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,…
Jul 2026 · github.com
- 8TO
Hi HN! We're Gabriel & Viraj, and we're excited to open source TensorZero. To be a little cheeky, TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products. 1. Integrate our model gateway 2. Send metrics or feedback 3. Unlock compounding improvements in quality, cost, and latency It enables a data & learning flywheel for LLMs by unifying: • Inference: one API for all LLMs, with <1ms P99 overhead • Observability: inference & feedback → your database • Optimization: better prompts, models, inference strategies • Experimentation:…
2024 · github.com
- 9CR
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).
2024 · github.com
- 10
Free, 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.
13d ago · inferquest.org
- 11LT
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…
2024 · github.com
- 12CM
Hey HN, I've been building AutoAgents, an AI agent framework in Rust. Today I'm sharing a feature I haven't seen done well elsewhere: composable middleware layers for LLM inference pipelines. The problem Every agent framework lets you swap LLM providers. Almost none of them give you a structured way to enforce safety, caching, or data sanitization in the inference path itself. You end up with guardrails as application-level if-statements, caching bolted on as a separate service, and PII handling as a "we'll add it later" TODO that never ships. This gets worse with local models. Cloud APIs…
Mar 2026 · github.com
- 13
- 14AE
2025 · github.com
- 15KP
I thought it'd be interesting to use Linux PSI (Pressure Stall Information) for an LLM runtime to trim the KV cache. This is mainly useful imo for edge devices like the Jetson Orin super nano kit which have unified memory. I haven't benched much, but plan to do so more over time and see if I can make a real use of it as I run local LLMs. Let me know if it makes sense :P (I of course vibed this idea)
Jun 2026 · github.com
- 16R5
Hi HN, I built OpenGraviton, an open-source AI inference engine that pushes the limits of running extremely large LLMs on consumer hardware. By combining 1.58-bit ternary quantization, dynamic sparsity with Top-K pruning and MoE routing, and mmap-based layer streaming, OpenGraviton can run models far larger than your system RAM—even on a Mac Mini. Early benchmarks: TinyLlama-1.1B drops from ~2GB (FP16) to ~0.24GB with ternary quantization. At 140B scale, models that normally require ~280GB fit within ~35GB packed. Optimized for Apple Silicon with Metal + C++ tensor unpacking, plus…
Mar 2026 · github.com
- 17LO
Hi HN! I built LLM OneStop (https://www.llmonestop.com), a unified interface for accessing multiple AI language models in one place. The main problem I wanted to solve: constantly switching between different AI platforms, managing multiple subscriptions, and losing conversation context when comparing outputs across models. Key features: Switch between GPT-4, Claude, Gemini, Llama, and other models mid-conversation Compare responses side-by-side Single interface instead of juggling multiple tabs/subscriptions Free tier available to try it out (no credit card needed) "Connect"…
Nov 2025 · llmonestop.com
- 18SY
Hey HN, If you tried running open-source models like Llama 3.1 70B or 405B, you might have noticed that it gets very expensive. The reason looks obvious enough that you might have stopped even before trying it! - GPUs are very expensive to buy or rent - Running the most performing LLMs need 4, 8 or even 16 top of the line Nvidia GPUs - And that won’t get you anywhere near the level of VRAM needed to batch enough to get a decent throughput and efficiency Some have even questioned if open-source LLM providers are not doing some shenanigans to provide the prices they offer. VC funded…
2024
- 19LP
I built llmswap to solve a problem I kept hitting in hackathons - burning through API credits while testing the same prompts repeatedly during development. It's a simple Python package that provides a unified interface for OpenAI, Anthropic, Google Gemini, and local models (Ollama), with built-in response caching that can cut API costs by 50-90%. Key features: - Intelligent caching with TTL and memory limits - Context-aware caching for multi-user apps - Auto-fallback between providers when one fails - Zero configuration - works with environment variables from llmswap import LLMClient client…
2025 · pypi.org
- 20IB
Hey HN, I've been working on something cool that I wanted to share with you all. It's called Viewpoint, an analytics tool for LLMs like OpenAI, Anthropic models, and Gemini. The idea came from the constant flood of new LLM models and the need to figure out which ones work best for my projects without breaking the bank. With viewpoint, I can track token usage, costs, latency(WIP), and traffic over time, making it easier to compare different models and see which ones perform best and save money. The tool works asynchronously, so it doesn't add any latency to your LLM requests, and you have…
2024 · viewpointhq.com
- 21
- 22AO
I've built an airgapped Retrieval-Augmented Generation (RAG) system for question-answering on documents, running entirely offline with local inference. Using Llama 3, Mistral, and Gemini, this setup allows secure, private NLP on your own machine. Perfect for researchers, data scientists, and developers who need to process sensitive data without cloud dependencies. Built with Llama C++, LangChain, and Streamlit, it supports quantized models and provides a sleek UI for document processing. Check it out, contribute, or suggest new features!
2024 · github.com
- 23LS
Hi HN, I built llm.sql, an LLM inference framework that reimagines the LLM execution pipeline as a series of structured SQL queries atop SQLite. The motivation: Edge LLMs are getting better, but hardware remains a bottleneck, especially RAM (size and bandwidth). When available memory is less than the model size and KV cache, the OS incurs page faults and swaps pages using LRU-like strategies, resulting in throughput degradation that's hard to notice and even harder to debug. In fact, the memory access pattern during LLM inference is deterministic - we know exactly which weights are needed…
Apr 2026
- 24LF
I submitted an earlier version of this a few months ago (as llama2.f90). At that time it had a lot of steps to run and was just a toy, now it's easy to run and is a competitive option for llm inference. See the motivation section for discussion and the `Performance` issue for an ongoing discussion about performance.
2023 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →