> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tensormesh.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Compatibility Matrix / Supported Models

> Models, serving engines, cache features, and recovery scenarios supported on the latest Tensormesh release — and the exact versions to deploy.

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.

| Cache engine | Operator | Helm chart | Serving image                |          Status          | As of      |
| ------------ | -------- | ---------- | ---------------------------- | :----------------------: | ---------- |
| `v0.5.3`     | `v0.5.3` | `0.5.3`    | `lmcache/vllm-openai:v0.5.3` |        ✅ Supported       | 2026-08-14 |
| `v0.5.3`     | `v0.5.3` | `0.5.2`    | `lmcache/vllm-openai:v0.5.3` |        ✅ Supported       | 2026-08-13 |
| `v0.5.2`     | `v0.5.2` | `0.5.2`    | `lmcache/vllm-openai:v0.5.2` |        ✅ Supported       | 2026-07-29 |
| `v0.5.4`     | `v0.5.3` | `0.5.3`    | `lmcache/vllm-openai:v0.5.4` | 🚧 Upgrade in validation | 2026-08-25 |

*Current as of **2026-08-25**.*

<Warning>
  Deploy these versions together and pin them explicitly — never `latest`.
  Mixing versions across the cache engine, operator, and chart is not supported.
</Warning>

# Model Support

In Tensormesh Operator we distinguish what is verified and supported. A **<u>verified</u>** model or feature means it is part and tested as part of Tensormesh CI. It is ready for production. A **<u>supported</u>** 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

| Model family | Models                                          |
| ------------ | ----------------------------------------------- |
| Kimi         | Kimi K3, Kimi K2.7, Kimi K2.5                   |
| GLM          | GLM-5.2, GLM-5.1, GLM-4.7, GLM-4.5, GLM-4       |
| Qwen         | Qwen3.6 , Qwen3.5, Qwen3                        |
| DeepSeek     | DeepSeek V4 Flash, DeepSeek V4 Pro, DeepSeek R1 |
| MiniMax      | MiniMax M3, MiniMax M2.7, MiniMax M2.5          |
| Gemma        | Gemma4, Gemma3                                  |
| gpt-oss      | gpt-oss-20b, gpt-oss-120b                       |
| llama        | llama 3.1                                       |

### CacheBlend

| Model family | Models                    |
| ------------ | ------------------------- |
| GLM          | GLM-5.2                   |
| MiniMax      | MiniMax M3, MiniMax M2.5  |
| Gemma        | Gemma3                    |
| gpt-oss      | gpt-oss-20b, gpt-oss-120b |
| llama        | llama 3.1                 |

## Tensormesh Operator Verified

### CPU offloading performance

CPU offloading performance speed up verified in the current release.

| Model             | Status         |
| ----------------- | -------------- |
| Deepseek r1 1.5b  | ✅ VERIFIED     |
| glm 4 9b          | ✅ VERIFIED     |
| glm 5.2           | ✅ VERIFIED     |
| Minimax m3        | ✅ VERIFIED     |
| Qwen3 0.6B        | ✅ VERIFIED     |
| Qwen3.6 27b       | ✅ VERIFIED     |
| Deepseek v4 Flash | ⚠️ Known issue |

### Cache features & External storage

Cache and storage capabilities available on the current release.

| Capability                         | Type       | Status     |
| ---------------------------------- | ---------- | ---------- |
| l2 Encryption                      | —          | ✅ VERIFIED |
| L2 filesystem offload (fs\_native) | Filesystem | ✅ VERIFIED |
| Payload Injection                  | —          | ✅ VERIFIED |

<Note>On the roadmap: GPUDirect Storage (GDS), pd Disaggregation, Peer-to-peer KV transfer.</Note>

### CacheBlend

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

| Model         | Status         |
| ------------- | -------------- |
| gpt oss 120b  | ⚠️ Known issue |
| llama-3.1-70B | ⚠️ Known issue |

### Serving engines

Serving engines supported in front of the Tensormesh cache.

| Serving engine | Notes                        | Status     |
| -------------- | ---------------------------- | ---------- |
| NVIDIA Dynamo  | —                            | ✅ VERIFIED |
| vLLM           | Bundled in the serving image | ✅ VERIFIED |

<Note>On the roadmap: SGLang, TensorRT-LLM, vLLM via stack-operator.</Note>

### Resilience

Failures Tensormesh detects and recovers from automatically.

| Scenario                          | Status     |
| --------------------------------- | ---------- |
| Cache engine pod failure recovery | ✅ VERIFIED |
| Coordinator pod Kill              | ✅ VERIFIED |
| Operator pod failure recovery     | ✅ VERIFIED |
| Vllm pod Kill                     | ✅ VERIFIED |