Technology

WEKA

WEKA is an AI-native, software-defined parallel storage platform (WekaFS) that presents a single namespace across NVMe flash with S3, POSIX, NFS, and SMB access. In 2026 its center of gravity shifted from "fast filesystem for AI training" to **inference-memory infrastructure**: the **Augmented Memory Grid** pools NVMe across nodes via a custom user-space RTOS and RDMA, and offloads the LLM **KV-cache** from GPU HBM to that persistent tier with sub-millisecond retrieval — a measured **7.5 million read IOPS**. It is one of the principal vendors defining the [Inference Context Memory Storage](/node/inference-context-memory-storage-icms) ("Tier 3.5") layer alongside VAST, Dell, and HPE.

10 connections2 posts

Definition

What it is

WEKA is an AI-native, software-defined parallel storage platform (WekaFS) that presents a single namespace across NVMe flash with S3, POSIX, NFS, and SMB access. In 2026 its center of gravity shifted from "fast filesystem for AI training" to inference-memory infrastructure: the Augmented Memory Grid pools NVMe across nodes via a custom user-space RTOS and RDMA, and offloads the LLM KV-cache from GPU HBM to that persistent tier with sub-millisecond retrieval — a measured 7.5 million read IOPS. It is one of the principal vendors defining the Inference Context Memory Storage ("Tier 3.5") layer alongside VAST, Dell, and HPE.

Why it exists

WEKA is a load-bearing example of the thesis this index tracks — object/flash storage becoming an active extension of GPU memory rather than a cold archive. By letting serving engines page KV-cache to a shared RDMA-attached NVMe tier instead of pinning it in ~$100/GB HBM, WEKA lets a cluster hold context for multi-turn agentic sessions across days while keeping GPUs saturated. Its S3 interface makes that tier interoperable with the rest of the object-storage ecosystem rather than a proprietary island.

Primary use cases

KV-cache offload / persistence for high-concurrency LLM inference; AI-training data delivery that keeps GPUs fed; RAG and agent-memory backends needing sub-ms retrieval at scale; mixed POSIX+S3 pipelines on one namespace.

Connections10

Outbound9
Inbound1
competes_with1

Featured in