This website has been temporarily rate limited | www.warman.life

kept by eddie apr 28

Open-weight models from China are commoditizing AI capability, breaking the monopoly moat of US closed labs, prompting protectionist moves that will harm long-term US competitiveness.

datalab-to/surya-ocr-2
Surya OCR 2 is a 650M-parameter vision-language model achieving 83.3% on olmOCR-bench and 87.2% on a 91-language benchmark, offering layout analysis, table recognition, and OCR in a single model.
also on vLLM, Llama.cpp, #open-source, #ai
Unsloth Studio | Hacker News
Unsloth launches Unsloth Studio, an open-source, no-code web UI for locally running, training, and exporting 500+ open models with 2x faster training and 70% less VRAM.
also on Llama.cpp, Ollama, #open-source, #ai
Running local models is good now
Local agentic coding models have reached surprising quality and usability over the past six months, now offering ~75% of frontier-model accuracy for many development tasks on a 64GB M2 Mac.
also on Llama.cpp, Ollama, #open-source
How prompt caching works - Paged Attention and Automatic Prefix Caching plus practical tips
The article explains how prompt caching works through vLLM's paged attention and automatic prefix caching, detailing KV-cache reuse and practical tips for improving cache hits.
also on vLLM, OpenAI, Anthropic, #open-source
Introducing Ossature: Spec-Driven Code Generation — Ossature Blog
Ossature is an open-source spec-driven code generation harness that validates specs, audits them for ambiguities, produces a reviewable build plan, and generates code with narrow context and deterministic boundaries.
also on Ollama, OpenAI, Anthropic, #open-source, #ai