Собираем домашний сервер для локальных LLM на доступных GPU (NVIDIA CMP 50HX)
Привет! Меня зовут Александр Щербаков, я DevOps-инженер в X5 Tech. В одной из прошлых статей я рассказывал о домашних серверах на потребительском же…
DevOps
⚑ Report a ProblemLatest DevOps news from Tech News
All topics
agents
ai
api
architecture
automation
aws
backend
beginners
cloud
database
devchallenge
devops
docker
javascript
kubernetes
llm
machinelearning
mcp
node
opensource
performance
productivity
programming
python
security
showdev
testing
tutorial
typescript
webdev
Зачем Авито нужна своя Inference-платформа для ML/LLM-сервисов: PaaS vs отдельное решение
Привет, Хабр! Меня зовут Антон Алексеев , я ML Ops-инженер в Авито . В этой статье я разберу, почему существующий PaaS — отличный инструмент для веб…
Сколько стоит суверенитет
Коллеги всю неделю обсуждают релиз претрейна https://huggingface.co/yandex/AliceAI-Foundation-80B-A3B-Base https://habr.com/en/companies/yandex/arti…
On-Device AI in Kotlin
In this Kotlin tutorial, you'll learn how to run a large language model (LLM) directly on a user's device: no server, no API key needed. We'll start…
I Got 28 TPS Out of Free Kaggle GPUs. Here's What It Took.
I want to be upfront about something: this whole project runs on free Kaggle T4 notebooks, an AWS EC2 t3.micro relay that costs almost nothing, and…
Speculative Decoding and MTP: Why Guessing Is Free
I saw "MTP round-trip" on a checklist for a Megatron conversion pipeline and had no idea what it meant. Two acronyms, one hyphen, apparently importa…
Как мы внедрили AIOps для контроля GPU‑утилизации и повысили её на 60%
Привет, Хабр! На связи Даниил Понизов и Роман Лазовский , руководитель и MLOps-инженер команды ML-платформы в RWB. Мы занимаемся разработкой платфор…
what a turn actually costs me
Four models read every frame Harness sees. CLIP embeds it. PaddleOCR pulls the text. A dense-text model embeds that. A reranker sorts results when y…
local-llm: A Field Report on Running SOTA Models on Your Own Hardware
The most useful thing in jamesob/local-llm is not the GPU shopping list. It is the fifteen or so BIOS settings, kernel flags, and PCIe hacks that st…
Two labs race to make AI write whole paragraphs at once instead of word by word
Diffusion text models — which draft an entire block of text at once and then iteratively refine it, rather than generating one token at a time left…
KV Cache Is Eating Your VRAM — Here's How to Estimate It Before You Run Out
Every LLM inference engineer hits this wall eventually. You deployed a model, it works in testing, then production traffic arrives. Suddenly your 80…
Lossless, But Not Free: The Lossless, But Not Free — When Speculative Decoding Actually Pays Off (and When It Doesn't)
One of the hottest topics in LLM inference acceleration right now is Speculative Decoding . DSpark claims 60%–85% single-user speedup at the same th…
96% of cuBLAS, no `unsafe`: what cuTile Rust proves
GPU programming usually asks Rust developers to surrender the borrow checker at the launch boundary: references collapse into raw pointers, and alia…
Sipp: a local-first runtime for Hybrid AI Applications
Over the past few months, I had the opportunity to contribute to llama.cpp’s WebGPU backend, helping push it from isolated operator support toward a…
Can You Tell When an LLM API Swaps in a Cheaper Model?
If you call an open-weight model behind an API, whether that is your own box, a hosted endpoint, or a router, you are trusting that the thing answer…
How to Build a Secure Homelab for LLM Inference
We’ve treated local AI deployments as experimental toys for too long. The moment a homelab becomes a dependency for work, the security posture must…
Speculative decoding: when and why it actually speeds up inference
Speculative decoding: when and why it actually speeds up inference Your chat endpoint serves 200 requests per second. The model is a 70B Llama 3 fin…
[Перевод] Дезагрегированный инференс LLM в Kubernetes: префилл, декодирование и планирование подов
С ростом сложности рабочих нагрузок инференса больших языковых моделей (LLM) единый монолитный процесс обслуживания упирается в свои пределы. У преф…