The speed-of-light optimization for Qwen3.5 on the TokenSpeed inference engine is a significant milestone, achieving a record-breaking 580 tokens per second (tps) for agentic workloads on NVIDIA GPUs. In the PyTorch Foundation's latest community blog post, you can learn all about the complete design, implementation, and optimization of Qwen3.5 models in the TokenSpeed inference framework and see for yourself how this work is improving performance 👉 bit.ly/4uGUvIS This achievement was a joint effort between the @Alibaba_Qwen inference team, @lightseekorg Foundation TokenSpeed team, @NVIDIAAI , and the Mooncake team, with special contributions from @tri_dao for FlashAttention-4 (FA4) optimization. @KVCache_AI

Introducing TokenSpeed, a speed-of-light LLM inference engine. > TensorRT LLM level performance > vLLM level usability > Built by a lean and mission-driven team in two months > MIT license, open-source github.com/lightseekorg/toke… lightseek.org/blog/lightseek…

🚀 New on the @vllm_project blog: Serving Agentic Workloads at Scale with vLLM x Mooncake. Agentic traces grow to 80K tokens with 94% reusable prefixes, but local KV caches evict them and cross-instance routing misses them. By integrating Mooncake Store as a distributed KV cache pool, vLLM gets: 🚀 3.8x higher throughput ⚡ 46x lower P50 TTFT ⏱️ 8.6x lower E2E latency 📈 Cache hit rate 1.7% -> 92.2% 🌐 Scales near-linearly to 60 GB200 GPUs at >95% hit rate 🔥 Powered by a deep collaboration between @Inferact and @KT_Project_AI 📖 Read more: vllm.ai/blog/mooncake-store 🧵👇

🚀TorchSpec has been live for 2 weeks — and kimi-k2.5-eagle3 just hit 40K downloads on HuggingFace! Thanks to @KT_Project_AI Team and @vllm_project Team for the amazing collaboration. Links in comments.

We’re excited to introduce TorchSpec, a torch-native framework for scalable speculative decoding training developed by the TorchSpec and Mooncake teams. By streaming hidden states from inference engines to training workers via Mooncake, TorchSpec enables fully disaggregated pipelines where inference and training scale independently. 🔗 Read our latest blog from TorchSpec & Mooncake teams: pytorch.org/blog/torchspec-s… @lightseekorg @KT_Project_AI #PyTorch #TorchSpec #Mooncake #OpenSourceAI

🚀 Our new blog: 1.53X over GB200 - Deploying DeepSeek on GB300 NVL72, with 226 TPS/GPU on long-context inference! Together with @nvidia, we have achieved new milestones on GB300 NVL72 for 128K/8K long-context serving: ⚡ 226 TPS/GPU peak throughput (1.53X vs GB200) 🧠 1.87X TPS/User gain with MTP under matched throughput 💾 1.6X higher decode batch size via GB300's 288GB HBM3e ⏱ 8.6s TTFT for 128K prefill with dynamic chunked PP 🔧 1.35X faster FMHA kernel via 2x SFU softmax throughput on Blackwell Ultra Powered by: PD disaggregation Wide-EP chunked PP MTP overlap scheduling FP8 attention, and orchestrated with NVIDIA Dynamo @NVIDIAAIDev

🚀 Qwen3.5-397B-A17B is here: The first open-weight model in the Qwen3.5 series. 🖼️Native multimodal. Trained for real-world agents. ✨Powered by hybrid linear attention   sparse MoE and large-scale RL environment scaling. ⚡8.6x–19.0x decoding throughput vs Qwen3-Max 🌍201 languages & dialects 📜Apache2.0 licensed 🔗Dive in: GitHub: github.com/QwenLM/Qwen3.5 Chat: chat.qwen.ai API：modelstudio.console.alibabac… Qwen Code: github.com/QwenLM/qwen-code Hugging Face: huggingface.co/collections/Q… ModelScope: modelscope.cn/collections/Qw… blog: qwen.ai/blog?id=qwen3.5

Introducing M2.5, an open-source frontier model designed for real-world productivity. - SOTA performance at coding (SWE-Bench Verified 80.2%), search (BrowseComp 76.3%), agentic tool-calling (BFCL 76.8%) & office work. - Optimized for efficient execution, 37% faster at complex tasks. - At $1 per hour with 100 tps, infinite scaling of long-horizon agents now economically possible MiniMax Agent: agent.minimax.io API: platform.minimax.io CodingPlan: platform.minimax.io/subscrib…

MiniMax-M2.5 is now open source. Trained with reinforcement learning across hundreds of thousands of complex real-world environments, it delivers SOTA performance in coding, agentic tool use, search, and office workflows. Hugging Face: huggingface.co/MiniMaxAI/Min… GitHub: github.com/MiniMax-AI/MiniMa… Coding Plan: platform.minimax.io/subscrib… Intelligence with Everyone

We’re excited to welcome Mooncake to the PyTorch Ecosystem! Mooncake is designed to solve the “memory wall” in LLM serving. By integrating Mooncake’s high performance KVCache transfer and storage capabilities with PyTorch native inference engines like SGLang, vLLM, and TensorRT-LLM, it unlocks new levels of throughput and scalability for large language model deployments. Mooncake enables prefill decode disaggregation, global KVCache reuse, elastic expert parallelism, and serves as a fault tolerant PyTorch distributed backend. 🔗 hubs.la/Q042Zf9N0 #PyTorch #OpenSourceAI #LLM #AIInfrastructure

One-shot "Video to code" result from Kimi K2.5 It not only clones a website, but also all the visual interactions and UX designs. No need to describe it in detail, all you need to do is take a screen recording and ask Kimi: "Clone this website with all the UX designs." riyd2bvh7ofju.beta-ok.kimi.l…