본문으로 건너뛰기
AI NEWS JOURNAL
AI NEWS / SEARCH

뉴스 및 전체 검색

뉴스, 도구, 모델, 가이드, 주제, 워크플로, 프롬프트를 함께 검색합니다.

뉴스 기사 230

“AI Code Guide”

뉴스 기사

Context Engineering (Agent Memory) for AI Agents Starts with Retrieval

Agents waste time and context on clumsy searches, oversized results and stale data. Learn the retrieval techniques LangChain's Deep Agents harness uses to get the right context in.

LangChain · AI Agents · Window뉴스 읽기 ↗
뉴스 기사

b11888

common, grammar: add recursive depth limit, make it a requirement (#31153) * common, grammar: add recursive depth limit, make it a requirement * catch more recursive functions * common : tidy up peg parser changes * grammar : reject candidates in a loop, without a depth limit The depth limit in llama_grammar_reject_candidates_for_stack counted the code points of a vocab token, so any token of 256 chars or more was always rejected under a grammar, such as the 512-space token of GLM-4.7-Flash or the long space tokens of Laguna-S-2.1. The rejection now walks the code points with its own stack of levels instead of recursing: there is no limit and no stack risk, whatever the length of a token from the GGUF, and the masks match master. * grammar : track rejected candidates as indices into the in

LLaMA · Gemma · Apple뉴스 읽기 ↗
뉴스 기사

b11877

vulkan: Add a larger tile size for conv3d (coopmat2 only) (#29920) * vulkan: Add a larger tile size for conv3d (coopmat2 only) This adds a larger tile size, in practice it is only for coopmat2 where we don't need shared memory to store the output (would use more than 64KB). Add some additional representative backend tests. At least, this is what codex came up with from looking at sd.cpp Wan VAE. * only apply large tile size for newer driver versions **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11877/llama-b11877-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama

Output · Codex · Wan뉴스 읽기 ↗
뉴스 기사

Trace and evaluate Cursor agents with Langfuse, powered by ClickHouse

Connect Cursor to Langfuse to trace every agent turn, pinpoint expensive model and tool calls, and use evaluations to confirm a fix actually helps, with ClickHouse powering the analytics underneath.

Cursor · Attention · docs뉴스 읽기 ↗
뉴스 기사

Introducing the (blazing fast!) native TCP client for .NET

ClickHouse’s new native TCP client for .NET brings faster reads and inserts with fewer allocations, columnar APIs, POCO support, and a path to migrate from HTTP.

Rows · docs · Sessions뉴스 읽기 ↗
뉴스 기사

The official ClickHouse provider for Apache Airflow is now available

The official ClickHouse provider for Apache Airflow simplifies data workflows with standard SQL operators, bulk inserts, and shared setup across self-managed Airflow and Astronomer.

Specific · Rows · Astro뉴스 읽기 ↗
뉴스 기사

Wan2.1: generate videos with an API

Wan2.1 is the most capable open-source video generation model, producing coherent and high-quality outputs. Learn how to run it in the cloud with a single line of code.

Capable · Replicate · Released뉴스 읽기 ↗
뉴스 기사

Wan2.1 parameter sweep

We've been playing with Alibaba's WAN2.1 text-to-video model lately. What happens when you tweak those mysterious parameters? Let's find out.

Replicate · Wan · Output뉴스 읽기 ↗
뉴스 기사

Generate short videos with the Replicate playground

Create AI videos with a convenient workflow.

Replicate · Output · Prompt뉴스 읽기 ↗
뉴스 기사

Qwen2.5-Math: The world's leading open-sourced mathematical LLMs

GITHUB HUGGING FACE MODELSCOPE DISCORD 🚨 Qwen2.5-Math mainly supports solving English and Chinese math problems through CoT and TIR. We do not recommend using this series of models for other tasks. Introduction A month ago, we released the first series of mathematical LLMs - Qwen2-Math - of our Qwen family. Today, we have upgraded it and open-sourced Qwen2.5-Math series, including base models Qwen2.5-Math-1.5B/7B/72B, instruction-tuned models Qwen2.5-Math-1.5B/7B/72B-Instruct, and mathematical reward model Qwen2.

Hugging Face · Released · Vital뉴스 읽기 ↗