That'd be cool! Here's the PR: https://
github.com/vllm-project/v
llm/pull/22845
… (but should be merged very soon)
OPEN SOURCE
-
vLLM Pull Request 22845 Merged Soon
By
–
-

CulturalGround Open-Source Multilingual Cultural VQA Dataset Released
By
–
The code used for curating CulturalGround, the largest open-source multilingual cultural VQA dataset, is now publicly available. The proposed pipeline could greatly enhance factual understanding of a wide array of real-world entities in multimodal LLMs, at zero cost. 30M VQA
-
Grok 4 builds Gemma-3-270M chatbot with transformers.js
By
–
Grok 4 one shots building a gemma-3-270m chatbot with transformers.js
— AK (@_akhaliq) 15 août 2025
one click deploy in anycoder pic.twitter.com/zciwWazuEFGrok 4 one shots building a gemma-3-270m chatbot with transformers.js one click deploy in anycoder
-

Hugging Face Growth: 2M Models vs 500K Datasets Race
By
–
will we get first to 2M public models or half a million public datasets on @huggingface
? -

OpenAI releases gpt-oss models on Databricks platform
By
–
Last week, we announced @OpenAI
’s new gpt-oss-20B and gpt-oss-120B models are now live on Databricks! They bring chain-of-thought reasoning and tool use, best-in-class latency and cost efficiency through Mixture-of-Experts, plus a 131k context window for long docs and RAG. -
vLLM Merger Plans and SGLang Development Status
By
–
vLLM should be merged soon but no plans for SGLang at the moment
-
7-14B Dense Models Now Accessible on Consumer GPUs
By
–
7-14b dense models are usable by just about everyone – 3090/4090 GPUs; Macs; etc…
-
Qwen3 Coder distilled dense model would boost practical utility
By
–
Qwen3 Coder 30b/3bA would be so much more useful to so many people if it were distilled to a dense model though!
-
GPT-3, ChatGPT, Llama-3 and MCP Enable AI Agents
By
–
Multiple actually. GPT-3 ChatGPT Llama-3 MCP really enabled AI Agents