推理市场是全球增长最快的市场,并且正在分化。每一种模态都在发展自己的推理技术栈。
英伟达的数据中心收入在整个 2022 年都持平。随后 ChatGPT 上线。三年后:增长了 17 倍。
数据库也经历过同样的过程。最初的一个市场,后来分化成了关系型、文档型、键值型、图数据库、时序数据库、向量数据库以及其他类型。每个类别都反映了不同的工作负载需求:实时事务处理 vs. 批量分析,ACID 合规 vs. 最终一致性。
推理市场正在分化的原因相同:工作负载不同。图像和视频是计算密集型的。更长的上下文窗口需要更多内存来存储 KV cache。边缘设备有功耗限制。单一架构无法同时优化所有这些场景。
模型生态系统也反映了这一点。少数几个半衰期较长的主流大语言模型,与 Hugging Face 上超过 9 万个图像生成模型并存,每天都有新的变体出现。每种模型类型都有不同的服务需求,这进一步分化了基础设施。如今,我们看到以下几个细分领域:
延迟层级:实时、近实时与批量
延迟定义了三个不同的细分领域。实时(低于 100 毫秒)服务于语音助手、实时翻译和自动驾驶汽车。用户不愿等待,因此基础设施必须在地理上分布,并配备专用容量。
近实时(100 毫秒至 2 秒)涵盖聊天机器人、代码补全和搜索增强。目前大多数大语言模型应用都在这个范围内运行,通过批处理和队列优化吞吐量,同时不损害用户体验。
批量(数秒至数小时)处理大规模文档处理和内容生成。成本效率比速度更重要,因此工作负载会在非高峰时段使用竞价实例运行。
多模态(图像、视频、音频)
瓶颈发生了转移。对于聊天机器人,问题在于内存。模型需要将整个对话内容保存在其“脑海”中,并且随着每一轮对话,这个记忆会增长。对于图像和视频生成,问题在于原始算力。生成一张图像需要模型进行 50 次顺序传递。不同的架构,不同的约束,不同的基础设施。
边缘(设备端与本地部署)
隐私要求、连接限制和延迟敏感性将推理推向边缘设备。手机、工业传感器、医疗设备。苹果在设备端运行一个30亿参数的模型用于Apple Intelligence。特斯拉在功耗72瓦的FSD芯片上运行视觉模型。量化模型、专用芯片和有限内存带来了与云端推理不同的优化挑战。
数据库市场孕育了Oracle、MongoDB、Databricks和Snowflake。一个价值1000亿美元的推理市场以同样的方式分化,为类似的赢家创造了空间。
-
英伟达季度报告——数据中心收入从36亿美元(2022年第四季度)增长到623亿美元(2025年第四季度)。↩︎
-
Hugging Face 文生图模型——截至2026年4月,托管了超过90,000个文生图模型。↩︎
-
Grand View Research:2024年AI推理市场规模——2024年估计为972.4亿美元。↩︎
The inference market is the fastest growing market in the world & it’s splitting up. Each modality is developing its own inference stack.
NVIDIA’s data center revenue was flat through 2022. Then ChatGPT launched. Three years later : 17x growth.1
Databases did the same thing. What started as one market fragmented into relational, document, key-value, graph, time series, vector, & others. Each category reflects different workload requirements : real-time transactions vs batch analytics, ACID compliance vs eventual consistency.
The inference market is fragmenting for the same reason : workloads are different. Images & video are compute-heavy. Longer context windows demand more memory for KV cache. Edge devices have power constraints. A single architecture can’t optimize for all of them.
The model ecosystem reflects this. A few dominant LLMs with long half-lives sit alongside 90,000+ image generation models on Hugging Face, with new variants appearing daily.2 Each model type has different serving requirements, which fragments the infrastructure. Today, we see these segments :
Latency Tiers : Real-Time, Near-Real-Time, & Batch
Latency defines three distinct segments. Real-time (sub-100ms) serves voice assistants, live translation, & autonomous vehicles. Users won’t wait, so infrastructure must be geographically distributed with dedicated capacity.
Near-real-time (100ms-2s) covers chatbots, code completion, & search augmentation. Most LLM applications today operate here, where batching & queuing optimize throughput without degrading experience.
Batch (seconds to hours) handles document processing & content generation at scale. Cost efficiency matters more than speed, so workloads run during off-peak hours on spot instances.
Multimodal (Image, Video, Audio)
The bottleneck shifts. For chatbots, the problem is memory. The model holds the entire conversation in its head, & that memory grows with every turn. For image & video generation, the problem is raw compute. A single image requires 50 sequential passes through the model. Different architectures, different constraints, different infrastructure.
Edge (On-Device & On-Premise)
Privacy requirements, connectivity constraints, & latency sensitivity push inference to edge devices. Mobile phones, industrial sensors, medical devices. Apple runs a 3-billion-parameter model on-device for Apple Intelligence. Tesla runs vision models on FSD chips drawing 72 watts. Quantized models, specialized chips, & limited memory create different optimization challenges than cloud inference.
The database market produced Oracle, MongoDB, Databricks, & Snowflake. A $100B inference market3 fragmenting the same way creates room for similar winners.
-
NVIDIA Quarterly Reports - Data center revenue grew from $3.6B (Q4 2022) to $62.3B (Q4 2025). ↩︎
-
Hugging Face Text-to-Image Models - Over 90,000 text-to-image models hosted as of April 2026. ↩︎
-
Grand View Research : AI Inference Market Size 2024 - Estimated at $97.24B in 2024. ↩︎