ArtificialAnlys: DeepSeek V4.1 Flash agent throughput up to 1.5x on GB300 NVL72
ArtificialAnlys reports that DeepSeek V4.1 Flash running on NVIDIA GB300 NVL72 gained up to 1.5x tokens per second per agent over the past month on its AA-AgentPerf benchmark, which tests datacenter systems running realistic agentic coding workloads. A single agent reached 848 tok/s, up from 596 (1.42x), while throughput per GPU rose roughly 1.6x at about 80 tok/s per agent. ArtificialAnlys attributes the gains to 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.
ArtificialAnlys attributes the higher measured throughput to updates across the inference serving stack, highlighting the role of software and system configuration in DeepSeek V4.1 Flash performance on GB300 NVL72.
DeepSeek 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

#DeepSeek#DeepSeek V4.1 Flash#NVIDIA GB300 NVL72#vLLM#FlashInfer#NVIDIA Dynamo#ArtificialAnlys#AA-AgentPerf