Кратко: Cursor умеет подключать любой endpoint в формате OpenAI API (/v1/chat/completions). Локально это обычно Ollama, LM Studio или llama.cpp server — все они поднимают HTTP-сервер, а Cursor думает, что общается с OpenAI.
LLVM — это компиляторная инфраструктура (Clang, оптимизации), к LLM не относится. Скорее всего имелось в виду Ollama (или опечатка «Llama»).
Local inference for OpenAI gpt-oss-20b via llama.cpp and Vulkan.
| Model | Fits this GPU? | Notes |
|---|---|---|
| gpt-oss-20b | ✅ Yes | MXFP4 GGUF ~11.3 GiB; full GPU offload on 890M |
| gpt-oss-120b | ❌ No | Needs ~80 GB VRAM (or heavy CPU offload + 64 GB+ RAM) |
Date: 2026-06-14
Project: /home/devops/projects/tts
Runtime: omnivoice.cpp (GGML / llama.cpp stack)
Model: k2-fsa/OmniVoice → GGUF (Serveurperso/OmniVoice-GGUF)
| Item | Value |
| <!DOCTYPE html> | |
| <html> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <title>grok Chat Export</title> | |
| <style> | |
| body { | |
| font-family: Arial, sans-serif; | |
| max-width: 800px; |
| d94M9jK3lXm8MSmDb5w87AxBl7jGouxuw1w9R3T2DZ8= |
| -- Creates a function that is able to request any URL and return the response | |
| create or replace function get_http(url text, data json) returns text | |
| language plpython3u as | |
| $$ | |
| import requests | |
| response = requests.get(url, verify=False, json=data) | |
| return response.text | |
| $$; | |
| -- Test-example call a webhook with data and get the response |
| -- 1. Install | |
| -- apt-get update && apt-get install -f postgresql-plpython3-16 pip | |
| -- 2. Python extension | |
| CREATE EXTENSION plpython3u; | |
| -- 3. Install API python packages | |
| -- pip install http.client urllib3 --break-system-packages |
| FROM postgres:16 | |
| MAINTAINER Andriy Oblivantsev <eslider@gmail.com> | |
| # Set the environment variables | |
| ARG DEBIAN_FRONTEND=noninteractive | |
| ENV TZ "Europe/Madrid" | |
| ENV LANG en_US.UTF-8 | |
| ENV LANGUAGE en_US:en | |
| ENV LC_ALL en_US.UTF-8 |
This AWS Lambda service provides a streamlined workflow for authors and readers to interact with each other. It allows authors to sign up, configure their reader magnet, and integrate their email tool. It also allows readers to access the author's book landing page, confirm their email address, and access the exclusive content.
Author Sign-up: Authors come to the website to sign-up for the service and to configure/administer their reader magnet. The author account sign-up flow should simply be email and password. Admin has the ability to approve/reject/freeze accounts in order to save capacity for the 100 authors (in case a bunch of random people sign-up).
Author’s Book Landing Page Configuration: After an author is signed up, they have a landing page configuration capability that provides the inputs to their landing page that readers see for each of their books that contain an email magnet. Each book landing page should have the ability
| #!/bin/bash | |
| ## Install | |
| # apt-get install -y jq | |
| ## Create an key here: https://beta.openai.com/account/api-keys | |
| export OPENAI_API_KEY='sk-XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX' | |
| ## AI Model | |
| model=text-davinci-003 |