精选模型75
阶跃星辰 Step 5 Preview 在 NVIDIA GB300 上展现推理性能
原标题:Great to see Step 5 Preview delivering strong inference performance on NVIDIA GB300.
阶跃星辰转发 NVIDIA 对 Step 5 Preview 的介绍,这是其规模最大的开源权重发布。该模型为 600B MoE,面向可持续长达 24 小时的智能体任务,在 NVIDIA GB300 上使用 NVFP4 时推理速度接近 8K tokens/sec/GPU。NVIDIA 同时给出了 NVFP4 checkpoint 以及 SGLang、vLLM、NeMo Automodel 和 NVIDIA NIM 的部署与后训练入口。
推荐理由StepFun 最大规模开源权重模型,600B MoE 面向长时智能体任务,并给出 GB300 上的推理性能与部署入口。
Great to see Step 5 Preview delivering strong inference performance on NVIDIA GB300.
Looking forward to seeing what developers build with it.
恭喜 StepFun 发布 Step 5 Preview 🙌 这是他们规模最大的开放权重发布。 这个 600B MoE 模型专为处理最长可持续 24 小时的智能体任务而构建。 该模型在 NVIDIA GB300 上使用 NVFP4,运行速度接近 8K tokens/sec/GPU。 NVP4 checkpoint:https://huggingface.co/stepfun-ai/Step-5-Preview-NVFP4 使用 @SGL_project 部署 - https://docs.sglang.io/cookbook/autoregressive/StepFun/Step-5-Preview 或 @vLLM_project - https://recipes.vllm.ai/stepfun-ai/Step-5-Preview 使用 NeMo Automodel 进行后训练:https://github.com/NVIDIA-NeMo/Automodel/blob/main/docs/model-coverage/llm/stepfun-ai/step-5-preview.mdx 使用 NVIDIA NIM 通过单条命令运行它:https://catalog.ngc.nvidia.com/orgs/nim/nvidia/containers/vllm-model-free-nim-experimental/-
查看原文
Congrats to StepFun on Step 5 Preview 🙌 Their largest open weights release. The 600B MoE model is built to handle agent tasks lasting up to 24 hours. The model runs at nearly 8K tokens/sec/GPU on NVIDIA GB300 using NVFP4. NVP4 checkpoint: https://huggingface.co/stepfun-ai/Step-5-Preview-NVFP4 Deploy with @SGL_project - https://docs.sglang.io/cookbook/autoregressive/StepFun/Step-5-Preview or @vLLM_project - https://recipes.vllm.ai/stepfun-ai/Step-5-Preview Post-train with NeMo Automodel: https://github.com/NVIDIA-NeMo/Automodel/blob/main/docs/model-coverage/llm/stepfun-ai/step-5-preview.mdx Run it with NVIDIA NIM using a single command: https://catalog.ngc.nvidia.com/orgs/nim/nvidia/containers/vllm-model-free-nim-experimental/-
