#qwen

vLLM Tops the Artificial Analysis Leaderboard May 11, 2026 · 15 min read How vLLM built the leading deployments of DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B.

vLLM Tops the Artificial Analysis Leaderboard How vLLM built the leading deployments of DeepSeek V3.2, MiniMax-M2.5, and…

vLLM Tops the Artificial Analysis Leaderboard May 11, 2026 · 15 min read How vLLM built the leading deployments of DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B.

vLLM Tops the Artificial Analysis Leaderboard How vLLM built the leading deployments of DeepSeek V3.2, MiniMax-M2.5, and…

CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models

CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models Why this matters Frontier models …

Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model

22nd April 2026 - Link Blog Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model (via) Big claims from Qwen about the…

Advancing Emerging Optimizers for Accelerated LLM Training with NVIDIA Megatron

Higher-order optimization algorithms such as Shampoo have been effectively applied in neural network training for at lea…

Accelerate Generative AI Inference on Amazon SageMaker AI with G7e Instances

Artificial Intelligence Accelerate Generative AI Inference on Amazon SageMaker AI with G7e Instances As the demand for g…

Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents

Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents TL;DR — We extend the RLVE framework fr…

TorchSpec: Speculative Decoding Training at Scale

Introduction Over the past year, large language models have rapidly expanded in both scale and capability. Frontier mode…

3/10/2026 Training-Inference Parity in MoE Models: Where Numerics Drift

On this page Kernel fusions that are mathematically equivalent can still drift numerically. Here are the parity bugs we …

Develop Native Multimodal Agents with Qwen3.5 VLM Using NVIDIA GPU-Accelerated Endpoints

Alibaba has introduced the new open source Qwen3.5 series built for native multimodal agents. The first model in this se…

1/13/2026 Best Open Source LLMs in 2026: We Reviewed 7 Models

With new open source LLMs launching nearly every week, figuring out which model actually fits your use case has become i…

Continuous batching from first principles

Continuous batching TL;DR: in this blog post, starting from attention mechanisms and KV caching, we derive continuous ba…

OVHcloud on Hugging Face Inference Providers 🔥

OVHcloud on Hugging Face Inference Providers 🔥 We're thrilled to share that OVHcloud is now a supported Inference Provi…

New coding models & integrations October 16, 2025 GLM-4.6 and Qwen3-coder-480B are available on Ollama’s cloud service with easy integrations to the tools you are familiar with. Qwen3-Coder-30B has been updated for faster, more reliable tool calling in Ollama’s new engine.

New coding models & integrations October 16, 2025 GLM-4.6 and Qwen3-coder-480B are available on Ollama’s cloud service w…

Qwen3-VL October 14, 2025 Ollama now supports Alibaba's Qwen3-VL.

Qwen3-VL October 14, 2025 Qwen3-VL, the most powerful vision language model in the Qwen series is now available on Ollam…

Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models

Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models TL;DR: Qwen3-8B is one of the most exci…

Scaleway on Hugging Face Inference Providers 🔥

Scaleway on Hugging Face Inference Providers 🔥 We're thrilled to share that Scaleway is now a supported Inference Provi…

vLLM Now Supports Qwen3-Next: Hybrid Architecture with Extreme Efficiency Sep 11, 2025 · 3 min read We’re excited to announce that vLLM now supports Qwen3-Next, the latest generation of foundation models from the Qwen team. Qwen3-Next introduces a hybrid architecture with extreme efficiency for...

vLLM Now Supports Qwen3-Next: Hybrid Architecture with Extreme Efficiency We’re excited to announce that vLLM now suppor…

Jupyter Agents: training LLMs to reason with notebooks

Jupyter Agents: training LLMs to reason with notebooks A natural way to display multi-step code execution together with …

Understanding and Implementing Qwen3 From Scratch

Understanding and Implementing Qwen3 From Scratch A Detailed Look at One of the Leading Open-Source LLMs Previously, I c…

From GPT-2 to gpt-oss: Analyzing the Architectural Advances

From GPT-2 to gpt-oss: Analyzing the Architectural Advances And How They Stack Up Against Qwen3 OpenAI just released the…

Qwen3 Coder 480B is Live on Cerebras August 01, 2025

Alibaba's Qwen3 Coder 480B Instruct model is now available on Cerebras. Qwen3 Coder is one of the top coding models in t…

Qwen3 235B 2507 Instruct Now Available on Cerebras July 29, 2025

Alibaba's Qwen3 235B 2507 Instruct model is now available on Cerebras. The world’s leading non-reasoning model – Qwen3 2…

Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models

Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models Numina & Kimi Team We're excited to announc…

SmolLM3: smol, multilingual, long-context reasoner

SmolLM3: smol, multilingual, long-context reasoner - Base model: https://hf.co/HuggingFaceTB/SmolLM3-3B-Base - Instruct …

Featherless AI on Hugging Face Inference Providers 🔥

Featherless AI on Hugging Face Inference Providers 🔥 We're thrilled to share that Featherless AI is now a supported Inf…

GroqCloud™ Now Supports Qwen3 32B

GroqCloud™ Now Supports Qwen3 32B Delivering Fast Inference with the Full 131k Context Window GroqCloud™ now supports Qw…

5/6/2025 Qwen 3 on Fireworks AI: Controllable Chain-of-Thought and Tool Calling at Frontier Scale

TL;DR - •Reasoning meets function calls. Qwen 3 now streams an explicit … trace and the exact JSON tool call in the same…

🐯 Liger GRPO meets TRL

Thank you for your great work. Anyway, I tested the liger loss with deepspeed zero3 using Qwen/Qwen2.5-0.5B-Instruct in …

The Transformers Library: standardizing model definitions

The Transformers Library: standardizing model definitions Transformers was created in 2019, shortly following the releas…

Improving Hugging Face Model Access for Kaggle Users

Improving Hugging Face Model Access for Kaggle Users Beginning today, Kaggle is launching an integration that enhances v…

The 4 Things Qwen-3’s Chat Template Teaches Us

The 4 Things Qwen-3’s Chat Template Teaches Us The new Qwen-3 model by Qwen ships with a much more sophisticated chat te…

FastRTC: The Real-Time Communication Library for Python

FastRTC: The Real-Time Communication Library for Python - OpenAI and Google released their live multimodal APIs for Chat…

Visual Document Retrieval Goes Multilingual

Visual Document Retrieval Goes Multilingual TL;DR: We presentvdr-2b-multi-v1 , the best multilingual embedding model for…

8/1/2025 Qwen3 Decoded: Choosing the Right Model For Your Task

With Thinking, Instruct, and Coder released simultaneously, confusion spiked. We stress-tested all three on your real wo…

SmolVLM - small yet mighty Vision Language Model

SmolVLM - small yet mighty Vision Language Model TLDR This blog post introduces SmolVLM, a 2B VLM, SOTA for its memory f…

SmolLM - blazingly fast and remarkably powerful

SmolLM - blazingly fast and remarkably powerful TL;DR This blog post introduces SmolLM, a family of state-of-the-art sma…

From cloud to developers: Hugging Face and Microsoft Deepen Collaboration

From cloud to developers: Hugging Face and Microsoft Deepen Collaboration A collaboration for Cloud AI Builders we are e…

RVPO: Risk-Sensitive Alignment via Variance Regularization

RVPO: Risk-Sensitive Alignment via Variance Regularization AuthorsIvan Montero, Tomasz Jurczyk, Bhuwan Dhingra RVPO: Ris…