3614 次浏览 · 33 赞 · 2 转发 （收录时）
DeepSeek V4.1 Flash 在 GB300 NVL72 上的速度提升最高达 1.5 倍
发生了什么
Artificial Analysis 报告称，在其 AA-AgentPerf 基准测试中，过去一个月 DeepSeek V4.1 Flash 在 GB300 NVL72 上的每个智能体 tok/s 速度最高提升了 1.5 倍。测得单个智能体的速度为 848 tok/s，高于此前的 596 tok/s；每个 GPU 的吞吐量也约为原来的 1.6 倍，每个智能体约为 80 tok/s。
接下来读什么
查看这件事的完整进展Artificial Analysis Reports Faster DeepSeek V4.1 Flash on GB300 NVL72DeepSeek V4.1 Flash speeds on GB300 NVL72 have increased by up to 1.5x tok/s per agent over the past month on AA-AgentPerf, our benchmark of datacenter systems running realistic agentic coding workloads
This improvement comes from a newer vLLM version, new vLLM kernels for DeepSeek V4.1 on GB300, FlashInfer autotuning, fuller CUDA graph coverage, tuned speculative decoding, and running prefill and decode on the same GPUs in NVIDIA’s updated Dynamo + vLLM setup
➤ Faster speeds: 848 tok/s for a single agent, up from 596 (1.42x)
➤ Higher throughput: ~1.6x the throughput per GPU at ~80 tok/s per agent
这件事到目前为止
Artificial Analysis reported that DeepSeek V4.1 Flash reached up to 1.5 times more tokens per second per agent on GB300 NVL72 over the past month, measured with its AA-AgentPerf benchmark of datacenter systems running realistic agentic coding workloads. It recorded 848 tokens per second for one agent, up from 596, and about 80 tokens per second per agent at roughly 1.6 times the throughput per GPU. Artificial Analysis attributed the improvement to a newer vLLM version and new vLLM kernels.
每天一封，跟上 AI 的重要变化
模型发布、价格变化、算力进展，附原始来源。免费，确认后开始发送，随时一键退订。 看一份往期日报 · 2026-11-07