- 谁
- InferenceX
- 引文
Compared with GB300 NVL72 running Dynamo + vLLM, InferenceX's perf ruler shows:
发生了什么
vLLM 公布了 DeepSeek V4.1 Flash 在 NVIDIA Vera Rubin NVL72 上的首批测试结果,该测试基于 SemiAnalysis 的 AgentX 基准测试,由 Dynamo 和 vLLM 提供支持。InferenceX 的性能标尺显示,在每用户 400 tok/s 时,单芯片总 token 吞吐量比 GB300 NVL72 高 63.4 倍;在每用户 600 tok/s 时,则高出 93.3 倍。
接下来读什么
查看这件事的完整进展vLLM Reports DeepSeek-V4.1-Flash Throughput on Vera Rubin NVL72The only thing faster than GB300 Dynamo + vLLM is Vera Rubin Dynamo + vLLM 🏎️💨.
The first DeepSeek V4.1 Flash results on @NVIDIA Vera Rubin NVL72 are here, powered by Dynamo + vLLM on @SemiAnalysis_'s AgentX benchmark.
Compared with GB300 NVL72 running Dynamo + vLLM, InferenceX's perf ruler shows:
- 63.4× total token throughput per chip at 400 tok/s/user
- 93.3× at 600 tok/s/user
这件事到目前为止
vLLM said it optimized DeepSeek-V4.1-Flash for NVIDIA's Vera Rubin NVL72 and reported higher token throughput than GB300 NVL72 on the SemiAnalysis AgentX benchmark, including results powered by Dynamo and vLLM. In its initial performance curve, vLLM measured 1.7 million tokens per second per GPU at 387 tokens per second per user at P90, or 58 times GB300 NVL72 throughput, along with a peak of 2.52 million tokens per second per GPU (2.7 times GB300 NVL72) and 1,810 tokens per second in a single concurrent session using TP 1/4. In a follow-up post, vLLM said InferenceX's performance ruler showed total token throughput per chip 63.4 times higher than GB300 NVL72 at 400 tokens per second per user and 93.3 times higher at 600 tokens per second per user.
