bump version to v0.12.0 (#4300)

* bump version to v0.12.0

* constraint transformers<5.0.0

* update supported models

* minor fix

Author: lvhan028

README.md

@@ -24,6 +24,13 @@ ______________________________________________________________________
 ## Latest News 🎉
 
 <details open>
+<summary><b>2026</b></summary>
+
+- \[2026/02\] Support [vllm-project/llm-compressor](https://github.com/vllm-project/llm-compressor) 4bit symmetric/asymmetric quantization. Refer [here](./docs/en/quantization/llm_compressor.md) for detailed guide
+
+</details>
+
+<details close>
 <summary><b>2025</b></summary>
 
 - \[2025/09\] TurboMind supports MXFP4 on NVIDIA GPUs starting from V100, achieving 1.5x the performmance of vLLM on H800 for openai gpt-oss models!
@@ -175,6 +182,7 @@ LMDeploy is a toolkit for compressing, deploying, and serving LLM, developed by
   <li>InternVL3.5 (1B-241BA28B)</li>
   <li>Intern-S1 (241B)</li>
   <li>Intern-S1-mini (8.3B)</li>
+  <li>Intern-S1-Pro (1TB)</li>
   <li>Mono-InternVL (2B)</li>
   <li>ChemVLM (8B-26B)</li>
   <li>CogVLM-Chat (17B)</li>
@@ -216,7 +224,7 @@ The default prebuilt package is compiled on **CUDA 12** since v0.3.0.
 For the GeForce RTX 50 series, please install the LMDeploy prebuilt package complied with **CUDA 12.8**
 
 ```shell
-export LMDEPLOY_VERSION=0.11.1
+export LMDEPLOY_VERSION=0.12.0
 export PYTHON_VERSION=310
 pip install https://github.com/InternLM/lmdeploy/releases/download/v${LMDEPLOY_VERSION}/lmdeploy-${LMDEPLOY_VERSION}+cu128-cp${PYTHON_VERSION}-cp${PYTHON_VERSION}-manylinux2014_x86_64.whl --extra-index-url https://download.pytorch.org/whl/cu128
 ```

README_zh-CN.md

@@ -24,15 +24,23 @@ ______________________________________________________________________
 ## 最新进展 🎉
 
 <details open>
-<summary><b>2025</b></summary>
+<summary><b>2026</b></summary>
+
+- \[2026/02\] 支持 [vllm-project/llm-compressor](https://github.com/vllm-project/llm-compressor) 4bit 对称和非对称量化。 具体操作指南详见[此处](./docs/zh_cn/quantization/llm_compressor.md)
+
 </details>
 
+<details close>
+<summary><b>2025</b></summary>
+
 - 【2025年9月】TurboMind 引擎支持 MXFP4，适用于 NVIDIA V100 及以上 GPU。在 H800 上推理 openai gpt-oss 模型，性能可达 vLLM 的 1.5倍！
 - 【2025年6月】深度优化 FP8 MoE 模型推理
 - 【2025年6月】集成[DLSlime](https://github.com/DeepLink-org/DLSlime)和[Mooncake](https://github.com/kvcache-ai/Mooncake)，实现DeepSeek PD分离部署，向两个团队表示诚挚的感谢！
 - 【2025年4月】集成deepseek-ai组件FlashMLA、DeepGemm、DeepEP、MicroBatch、eplb等，提升DeepSeek推理性能
 - 【2025年1月】新增对DeepSeek V3及R1的支持
 
+</details>
+
 <details close>
 <summary><b>2024</b></summary>
 
@@ -176,6 +184,7 @@ LMDeploy TurboMind 引擎拥有卓越的推理能力，在各种规模的模型
   <li>InternVL3.5 (1B-241BA28B)</li>
   <li>Intern-S1 (241B)</li>
   <li>Intern-S1-mini (8.3B)</li>
+  <li>Intern-S1-Pro (1TB)</li>
   <li>Mono-InternVL (2B)</li>
   <li>ChemVLM (8B-26B)</li>
   <li>CogVLM-Chat (17B)</li>
@@ -217,7 +226,7 @@ pip install lmdeploy
 若使用 GeForce RTX 50 系列显卡，请安装基于 **CUDA 12.8** 编译的 LMDeploy 预编译包。
 
 ```shell
-export LMDEPLOY_VERSION=0.11.1
+export LMDEPLOY_VERSION=0.12.0
 export PYTHON_VERSION=310
 pip install https://github.com/InternLM/lmdeploy/releases/download/v${LMDEPLOY_VERSION}/lmdeploy-${LMDEPLOY_VERSION}+cu128-cp${PYTHON_VERSION}-cp${PYTHON_VERSION}-manylinux2014_x86_64.whl --extra-index-url https://download.pytorch.org/whl/cu128
 ```

docs/en/get_started/installation.md

@@ -23,7 +23,7 @@ pip install lmdeploy
 The default prebuilt package is compiled on **CUDA 12**. If CUDA 11+ (>=11.3) is required, you can install lmdeploy by:
 
 ```shell
-export LMDEPLOY_VERSION=0.11.1
+export LMDEPLOY_VERSION=0.12.0
 export PYTHON_VERSION=310
 pip install https://github.com/InternLM/lmdeploy/releases/download/v${LMDEPLOY_VERSION}/lmdeploy-${LMDEPLOY_VERSION}+cu118-cp${PYTHON_VERSION}-cp${PYTHON_VERSION}-manylinux2014_x86_64.whl --extra-index-url https://download.pytorch.org/whl/cu118
 ```

docs/en/supported_models/supported_models.md

@@ -72,6 +72,7 @@ The following tables detail the models supported by LMDeploy's TurboMind engine
 |           InternLM3            |       8B        | LLM  |    Yes    |   Yes   |   Yes   | Yes  |  Yes  |
 |           Intern-S1            |      241B       | MLLM |    Yes    |   Yes   |   Yes   | Yes  |   -   |
 |         Intern-S1-mini         |      8.3B       | MLLM |    Yes    |   Yes   |   Yes   | Yes  |   -   |
+|         Intern-S1-Pro          |       1TB       | MLLM |    Yes    |    -    |    -    |  -   |  No   |
 |           Baichuan2            |       7B        | LLM  |    Yes    |   Yes   |   Yes   | Yes  |  No   |
 |           Baichuan2            |       13B       | LLM  |    Yes    |   Yes   |   Yes   |  No  |  No   |
 |            ChatGLM2            |       6B        | LLM  |    Yes    |   Yes   |   Yes   |  No  |  No   |

docs/zh_cn/get_started/installation.md

@@ -23,7 +23,7 @@ pip install lmdeploy
 默认的预构建包是在 **CUDA 12** 上编译的。如果需要 CUDA 11+ (>=11.3)，你可以使用以下命令安装 lmdeploy：
 
 ```shell
-export LMDEPLOY_VERSION=0.11.1
+export LMDEPLOY_VERSION=0.12.0
 export PYTHON_VERSION=310
 pip install https://github.com/InternLM/lmdeploy/releases/download/v${LMDEPLOY_VERSION}/lmdeploy-${LMDEPLOY_VERSION}+cu118-cp${PYTHON_VERSION}-cp${PYTHON_VERSION}-manylinux2014_x86_64.whl --extra-index-url https://download.pytorch.org/whl/cu118
 ```

docs/zh_cn/supported_models/supported_models.md

@@ -19,6 +19,7 @@
 |      InternLM-XComposer2.5       |       7B       | MLLM |    Yes    |   Yes   |   Yes   |  Yes  |
 |            Intern-S1             |      241B      | MLLM |    Yes    |   Yes   |   Yes   |  No   |
 |          Intern-S1-mini          |      8.3B      | MLLM |    Yes    |   Yes   |   Yes   |  No   |
+|          Intern-S1-Pro           |      1TB       | MLLM |    Yes    |    -    |    -    |  No   |
 |               Qwen               |   1.8B - 72B   | LLM  |    Yes    |   Yes   |   Yes   |  Yes  |
 |     Qwen1.5<sup>\[1\]</sup>      |  1.8B - 110B   | LLM  |    Yes    |   Yes   |   Yes   |  Yes  |
 |      Qwen2<sup>\[2\]</sup>       |   0.5B - 72B   | LLM  |    Yes    |  Yes\*  |  Yes\*  |  Yes  |

lmdeploy/version.py

@@ -1,7 +1,7 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 from typing import Tuple
 
-__version__ = '0.11.1'
+__version__ = '0.12.0'
 short_version = __version__
 
 

requirements/runtime_cuda.txt

@@ -23,7 +23,7 @@ shortuuid
 tiktoken
 torch<=2.8.0,>=2.0.0
 torchvision<=0.23.0,>=0.15.0
-transformers
+transformers<5.0.0
 triton<=3.4.0,>=3.0.0; sys_platform == "linux" and "aarch64" not in platform_machine and "arm" not in platform_machine
 uvicorn
 xgrammar