GPUStack v2.3.0 is out! 🚀
• Automatic PD orchestration
• Shared KV cache
• vGPU partitioning
• Model & backend OTA updates
• Scheduled scaling, smarter benchmarks & routing
Explore the release:
github.com/gpustack/gpust…
GPUStack
@GPUStack_ai
Manage GPU clusters for running LLMs github.com/gpustack/gpust…
- 🎉 Congrats to @MiniMax_AI on the release of MiniMax-M3.1-Flash! 🚀 Day-0 support is here in GPUStack. Deploy it on your own GPUs, give it a try, and let us know how it works for you! ⭐ github.com/gpustack/gpust…MiniMax M3.1 Flash weights are now public. 428B parameters total, 23B activated per token. Agentic performance: A generational leap in agentic tasks, coding, and cybersecurity — 76.2 on BankerToolBench, 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2, 29.6 on Agents' Last Exam, andMade with AI
- “I’m faster.” “At what?” 🦭 We brought @deepseek_ai’s DeepInfer to GPUStack and put it up against @vllm_project on 8× NVIDIA B200 GPUs. In our 16-concurrent-request test, DeepInfer delivered ~25% higher average output throughput—but vLLM had lower time to first token and P95
- DeepInfer meets GPUStack 🚀 On 8×B200, @deepseek_ai’s DeepInfer delivered 25.2% higher mean output throughput than @vllm_project, with longer time to first token. Initial results; neither setup fully tuned. GitHub: github.com/gpustack/DeepI… Join us on Discord:00:00🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more
- 🚀 DeepSeek-V4.1-Flash-1017 is now supported on GPUStack! Get started with self-hosted DeepSeek on your own infrastructure, with full control over where your model runs. 🔒 👉 github.com/gpustack/gpust…🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy,
