Skip to main content
This page lists what the current Tensormesh release supports: the models it serves, the serving engines it runs in front of, the cache and storage features it provides, and the failures it recovers from — along with the exact versions to deploy. Tensormesh is released and supported as a single matched set, so the versions below are the ones to run together.

​
Compatibility matrix

Tensormesh is released as a matched set. Deploy a single row’s versions together — the cache engine, operator, and Helm chart are supported as a unit. Current as of 2026-08-20.
Deploy these versions together and pin them explicitly — never latest. Mixing versions across the cache engine, operator, and chart is not supported.

​
Model Support

In Tensormesh Operator we distinguish what is verified and supported. A verified model or feature means it is part and tested as part of Tensormesh CI. It is ready for production. A supported model or feature requires testing prior to go on production as it is supported on LMCache opensource version but it has not been verified in our CI. In other word, we know/assume it works but it is not part of our CI process.

​
Supported models

​
CPU/Storage offloading

​
CacheBlend

​
Tensormesh Operator Verified

​
CPU offloading performance

CPU offloading performance speed up verified in the current release.

​
Cache features & External storage

Cache and storage capabilities available on the current release.
On the roadmap: GPUDirect Storage (GDS), Peer-to-peer KV transfer.

​
CacheBlend

Non-prefix KV cache reuse — cached chunks are reused at shifted positions (re-RoPE + partial recompute), beyond what prefix caching can do.

​
Serving engines

Serving engines supported in front of the Tensormesh cache.
On the roadmap: NVIDIA Dynamo, SGLang, TensorRT-LLM, vLLM via stack-operator.

​
Resilience

Failures Tensormesh detects and recovers from automatically.