# LMDeploy vs TorchServe

**Leader by vioscaleAI score:** TorchServe

| Attribute | LMDeploy | TorchServe |
|---|---|---|
| **vioscaleAI score** | 55.9 (64% (medium)) | 68.1 (76% (high)) |
| activity.commits_last_30d | 66 | 100 |
| adoption.dependent_repos | 2 | 92,053 |
| adoption.github_stars | 8,104 | 104,702 |
| content.faq | `[{"answer":"A software framework that enables developers to compress, deploy, and serve large language models with quantization optimization, multiple inference engines, and compatibility across various model architectures. It is indexed under Model Serving.","source":"https://lmdeploy.readthedocs.io/en/latest/","question":"What is LMDeploy?","confidence":0.6},{"answer":"LMDeploy is open source, so it can be self-hosted and used at no licence cost. It is released under the Apache-2.0 licence. Pricing changes often, so verify at source before relying on it.","source":"https://lmdeploy.readthedocs.io/en/latest/","question":"Is LMDeploy free to use?","confidence":0.6},{"answer":"LMDeploy supports Windows and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://lmdeploy.readthedocs.io/en/latest/","question":"What platforms does LMDeploy support?","confidence":0.6},{"answer":"Yes. LMDeploy can be deployed self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://lmdeploy.readthedocs.io/en/latest/","question":"Can LMDeploy be self-hosted?","confidence":0.6},{"answer":"Yes. LMDeploy is published under the Apache-2.0 licence, a permissive licence that generally allows commercial use and modification. Licence terms can change between releases, so verify against the repository for the version you intend to use.","source":"https://github.com/internlm/lmdeploy","question":"Is LMDeploy open source?","confidence":0.95}]` | `[{"answer":"TorchServe enables efficient production deployment of machine learning models at scale across different cloud platforms and infrastructure. It supports multi-model serving, provides monitoring and logging capabilities, and offers REST API endpoints for application integration. It is indexed under Model Serving.","source":"https://pytorch.org/serve/","question":"What is TorchServe?","confidence":0.6},{"answer":"TorchServe is open source, so it can be self-hosted and used at no licence cost. Pricing changes often, so verify at source before relying on it.","source":"https://pytorch.org/serve/","question":"Is TorchServe free to use?","confidence":0.6},{"answer":"TorchServe supports Windows, Linux and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://pytorch.org/serve/","question":"What platforms does TorchServe support?","confidence":0.6},{"answer":"Yes. TorchServe can be deployed cloud / SaaS and self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://pytorch.org/serve/","question":"Can TorchServe be self-hosted?","confidence":0.6},{"answer":"We have confirmed 6 integrations for TorchServe, including AWS Inferentia2, AWS SageMaker, Google Cloud Vertex AI, Google Cloud TPUv5, Intel oneAPI and Datadog. This is what we could verify from public sources, so the vendor may support others we have not indexed.","source":"https://pytorch.org/serve/","question":"What does TorchServe integrate with?","confidence":0.6}]` |
| deployment.options | `{"self_hosted":true}` | `{"cloud":true,"self_hosted":true}` |
| description.long | LMDeploy is a comprehensive toolkit enabling efficient compression, deployment, and serving of large language models across multiple machines and GPUs with advanced optimization techniques. | TorchServe enables deploying PyTorch models across cloud and on-premises environments, supporting simultaneous multi-model hosting, operational observability through logging and metrics, and HTTP endpoints for consuming models in applications. |
| features.capabilities | `{"gpu_acceleration":true,"continuous_batching":true,"multi_model_serving":true,"multi_gpu_multi_node":true,"quantization_support":true}` | `{"open_source":true,"gpu_acceleration":true,"multi_model_serving":true,"multi_gpu_multi_node":true,"quantization_support":true}` |
| integrations.count | 2 | 6 |
| integrations.list | `[{"name":"llm-compressor"},{"name":"OpenCompass"}]` | `[{"name":"AWS Inferentia2"},{"name":"AWS SageMaker"},{"name":"Google Cloud Vertex AI"},{"name":"Google Cloud TPUv5"},{"name":"Intel oneAPI"},{"name":"Datadog"}]` |
| language.primary | Python | Python |
| license.spdx | Apache-2.0 | - |
| platform.support | `{"cli":true,"windows":true}` | `{"cli":true,"ios":true,"linux":true,"android":true,"windows":true}` |
| pricing | `{"type":"open_source","freeTier":true,"sourceUrl":"https://lmdeploy.readthedocs.io/en/latest/","retrievedAt":"2026-08-20T12:17:08.568Z"}` | `{"type":"open_source","sourceUrl":"https://pytorch.org/serve/","retrievedAt":"2026-08-20T16:35:31.436Z"}` |
| pricing.free_tier | yes | - |
| pricing.model | open_source | open_source |
| pricing.price_level | free | free |
| release.cadence_days | 21 | 42 |
| release.history | `[{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.18.0","date":"2026-09-28T07:04:58Z","type":"stable","version":"v0.18.0"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.17.0","date":"2026-09-01T07:13:39Z","type":"stable","version":"v0.17.0"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0","date":"2026-08-19T04:43:53Z","type":"stable","version":"v0.16.0"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.15.0","date":"2026-07-31T13:00:46Z","type":"stable","version":"v0.15.0"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.14.0","date":"2026-06-24T04:36:56Z","type":"stable","version":"v0.14.0"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/0.14.0a2","date":"2026-06-16T04:16:04Z","type":"prerelease","version":"0.14.0a2"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/0.14.0a1","date":"2026-06-01T08:46:02Z","type":"prerelease","version":"0.14.0a1"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.13.0","date":"2026-05-12T03:46:57Z","type":"stable","version":"v0.13.0"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3","date":"2026-04-08T03:37:26Z","type":"stable","version":"v0.12.3"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.12.2","date":"2026-03-18T03:13:55Z","type":"stable","version":"v0.12.2"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.12.1","date":"2026-02-13T09:02:12Z","type":"stable","version":"v0.12.1"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.12.0","date":"2026-02-04T06:28:25Z","type":"stable","version":"v0.12.0"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.11.1","date":"2025-12-24T13:27:06Z","type":"stable","version":"v0.11.1"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.11.0","date":"2025-12-04T06:20:38Z","type":"stable","version":"v0.11.0"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.10.2","date":"2025-10-28T11:32:42Z","type":"stable","version":"v0.10.2"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.10.1","date":"2025-09-26T02:45:30Z","type":"stable","version":"v0.10.1"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.10.0","date":"2025-09-09T05:05:09Z","type":"stable","version":"v0.10.0"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.9.2.post1","date":"2025-08-19T09:44:41Z","type":"stable","version":"v0.9.2.post1"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.9.2","date":"2025-07-26T10:00:25Z","type":"stable","version":"v0.9.2"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.9.1","date":"2025-07-04T10:05:31Z","type":"stable","version":"v0.9.1"}]` | `[{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.14.1","date":"2026-09-30T19:14:48Z","type":"stable","version":"v2.14.1"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.14.0","date":"2026-09-02T17:40:10Z","type":"stable","version":"v2.14.0"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.13.0","date":"2026-07-08T17:39:58Z","type":"stable","version":"v2.13.0"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.12.1","date":"2026-06-18T00:41:17Z","type":"stable","version":"v2.12.1"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.12.0","date":"2026-05-13T17:38:06Z","type":"stable","version":"v2.12.0"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.11.0","date":"2026-03-23T18:38:28Z","type":"stable","version":"v2.11.0"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.10.0","date":"2026-01-21T17:05:16Z","type":"stable","version":"v2.10.0"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.9.1","date":"2025-11-12T19:27:19Z","type":"stable","version":"v2.9.1"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.9.0","date":"2025-10-15T17:12:27Z","type":"stable","version":"v2.9.0"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.8.0","date":"2025-08-06T17:06:10Z","type":"stable","version":"v2.8.0"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.7.1","date":"2025-06-04T18:13:15Z","type":"stable","version":"v2.7.1"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.7.0","date":"2025-04-23T16:16:06Z","type":"stable","version":"v2.7.0"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.6.0","date":"2025-01-29T17:18:54Z","type":"stable","version":"v2.6.0"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.5.1","date":"2024-10-29T17:58:24Z","type":"stable","version":"v2.5.1"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.5.0","date":"2024-10-17T16:26:53Z","type":"stable","version":"v2.5.0"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.4.1","date":"2024-09-04T19:59:29Z","type":"stable","version":"v2.4.1"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.4.0","date":"2024-07-24T18:39:28Z","type":"stable","version":"v2.4.0"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.3.1","date":"2024-06-05T19:16:07Z","type":"stable","version":"v2.3.1"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.3.0","date":"2024-04-24T16:12:17Z","type":"stable","version":"v2.3.0"},{"url":"https://github.com/pytorch/pytorch/releases/tag/v2.2.2","date":"2024-03-27T22:27:02Z","type":"stable","version":"v2.2.2"}]` |
| security.scorecard | - | 6.4 |
| security.vulnerabilities | `{"count":10,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=lmdeploy&per_page=100","last_12m":8,"max_severity":"CRITICAL"}` | `{"count":13,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=torch&per_page=100","last_12m":0,"max_severity":"CRITICAL"}` |

## Capabilities (Model Serving)

| Capability | LMDeploy | TorchServe |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Continuous batching | ✓ | - |
| Dynamic batching | - | - |
| Multi framework support | - | - |
| GPU acceleration | ✓ | ✓ |
| Multi GPU multi node | ✓ | ✓ |
| Quantization support | ✓ | ✓ |
| Openai compatible API | - | - |
| Autoscaling scale to zero | - | - |
| Multi model serving | ✓ | ✓ |
| Canary ab rollout | - | - |
| Kubernetes native | - | - |
| Open source | - | ✓ |

*Source: vioscaleAI. Generated 2026-10-16T20:14:32.282Z. "-" = undocumented, not absent.*