Menu

#Llm

757 posts

2 points
Feed·
20 of 757 posts
Điểm tin Trí tuệ Nhân tạo & Mô hình Ngôn ngữ lớn (LLMs) tại Việt Nam (18/11/2026)
📰
0Read More

Điểm tin Trí tuệ Nhân tạo & Mô hình Ngôn ngữ lớn (LLMs) tại Việt Nam (18/11/2026)

DEV Community: ai·Vu Hung Nguyen (Hưng)·1 day ago
#wWX3Vgd8
#devtoai#devto#dev#vietnam#ai

Điểm tin Trí tuệ Nhân tạo & Mô hình Ngôn ngữ lớn (LLMs) tại Việt Nam (18/11/2026) Bản...

15s
I built HexCore — an ultra-lightweight, zero-dependency Paged & Quantized (FP16 / INT4 / INT2) KV-Cache Engine written in pure C++ and CUDA.
📰
0Read More

I built HexCore — an ultra-lightweight, zero-dependency Paged & Quantized (FP16 / INT4 / INT2) KV-Cache Engine written in pure C++ and CUDA.

DEV Community: cpp·Rasuljanov Muhammadali·2 days ago
#7YZlxZit
#devtocpp#devto#dev#cpp#llm

While production serving stacks like vLLM @FlashInfer SGLang, and LMDEploy are powerhouse frameworks,...

15s
I Built an Open-Source Observatory for Windows: Here's Why Browsing GitHub Needed a Redesign
🖼️
0Read More

I Built an Open-Source Observatory for Windows: Here's Why Browsing GitHub Needed a Redesign

DEV Community: opensource·VinayKumar·4 days ago
#Ww2vfyu7
#devtoopensource#devto#dev#llm#rust

Imagine walking into a massive library where every interesting book you touch forces you to open a...

15s
0Read More

MinusPod now turns YouTube playlists and channels into ad-free podcast feeds (SponsorBlock first, LLM as fallback)

MinusPod is a self-hosted server that strips ads out of podcasts before they reach your player: it transcribes each episode locally, an LLM finds the ad reads, and the cut audio is served back as a normal RSS feed.…

15s
Self-hosted LLM on Hostinger KVM2: under 10s responses, 2 CPU cores, no GPU. Here's how!
📰
0Read More

Self-hosted LLM on Hostinger KVM2: under 10s responses, 2 CPU cores, no GPU. Here's how!

DEV Community: backend·Muhammad Sheeraz·21 days ago
#GW9KH4ft
#devtobackend#devto#dev#ai#llm

Optimizing a Local RAG Chatbot for CPU Inference Tags: #ai #llm #rag #python Building a...

15s
0Read More

Sowjanya Pandruju on Managing Agent State – Software Engineering Radio

#ai#database#llm#seradio#agents

Sowjanya Pandruju, Cloud Application Architect with Amazon Web Services, Vice Chair of the IEEE Computer Society Madison Section, and Chair of the IEEE Women in Engineering (WIE) Madison Section (Region 4), speaks with SE Radio host Gavin Henry about…

15s
Language Models for Text Classification: From Bag-of-Words to Jev
🖼️
213Read More

Language Models for Text Classification: From Bag-of-Words to Jev

Hacker News·about 2 months ago
#P5jggCFw
#magazine#jev#llm#classifier#article

A Visual Guide to RNNs, CNNs, Transformers, and Calibration, with Hands-On Experiments on Accuracy and Efficiency

15s