AITOPAI热报
ModelsSelected73°

DeepSeek V4.1 Flash model released

DeepSeek V4.1 Flash 模型正式发布，支持原生多模态视觉理解

IT之家
Blog/Media
Read the original
Why we picked it

Cost-effective for developers needing multimodal capabilities, with lower input activation costs than comparable models.

DeepSeek launched the V4.1 Flash model on 10 Sep 2024, the smallest in its new model series. The 552B parameter MoE model features native multimodal visual understanding and a new Causal-Encoder-Decoder structure. It achieved higher intelligence than flagship models including DeepSeek V4 Pro in Agentic Benchmark testing.

Original · IT之家

DeepSeek V4.1 Flash 模型正式发布，支持原生多模态视觉理解

IT之家 9 月 10 日消息，深度求索今日正式发布 DeepSeek V4.1 Flash 模型 。这是其全新模型结构系列中的最小尺寸的模型，具备原生多模态视觉理解能力。 新模型结构的设计初衷是：能力上限更高、推理速度更快、吞吐更大、可扩展到更大参数模型。 DeepSeek V4.1 Flash 为 552B 参数的 MoE 模型 ，采用了全新的 Causal-Encoder-Decoder 结构，输入和输出不对称，输入激活只有 8B，输出激活 16B，成本显著低于已知的同尺寸模型。同时，V4.1 Flash 还采用了新的预训练方式、经过了更大规模的强化学习后训练，在基准测试中，成功超越了包括 DeepSeek V4 Pro 在内的一众旗舰模型的智能水平。 ▲ DeepSeek-V4.1-Flash 与主流前沿模型在 Agentic Benchmark 上的性能对比

#DeepSeek#V4.1 Flash#multimodal#MoE#Agentic Benchmark

Keep reading

Recent stories with the same tag or section
ProductsUS vs ChinaSelected07:26
vLLM sets best DeepSeek-V4.1-Flash result on SemiAnalysis AgentX

Matching DeepInfer's performance while beating it on a third-party agentic benchmark suggests vLLM is now a credible production backend for high-throughput DeepSeek serving, not just a research engine. Engineers running agent-heavy inference stacks can use the reproducible blog recipe to benchmark their own deployments against the 954K tokens/s figure. DeepSeek's off-peak pricing makes the revenue-per-GPU-hour number a useful cost baseline for capacity planning.

#vLLM#DeepSeek#AgentX#SemiAnalysis
官方账号vLLM@vllm_projectSource
ModelsBuildersSelected02:02
vLLM Matches DeepInfer on DeepSeek-V4.1-Flash Decode

An open-source inference stack catching up with a frontier lab's in-house engine means teams can serve DeepSeek-V4.1-Flash without relying on the vendor's own tooling. Engineers running self-hosted deployments in Singapore or ASEAN data centres can benchmark vLLM at DEP32 as a direct alternative to DeepInfer's EP64DP64 setup, avoiding engine lock-in while keeping comparable throughput at large batch sizes.

#vLLM#DeepSeek#DeepInfer#inference
官方账号vLLM@vllm_projectSource