bump version to v0.12.2

README.md

@@ -176,7 +176,7 @@ LMDeploy is a toolkit for compressing, deploying, and serving LLM, developed by
   <li>Qwen2-VL (2B, 7B, 72B)</li>
   <li>Qwen2.5-VL (3B, 7B, 72B)</li>
   <li>Qwen3-VL (2B - 235B)</li>
-  <li>Qwen3.5</li>
+  <li>Qwen3.5 (27B - 397B)</li>
   <li>DeepSeek-VL (7B)</li>
   <li>DeepSeek-VL2 (3B, 16B, 27B)</li>
   <li>InternVL-Chat (v1.1-v1.5)</li>
@@ -228,7 +228,7 @@ 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=0.12.1
+export LMDEPLOY_VERSION=0.12.2
 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_ja.md

@@ -155,7 +155,7 @@ LMDeploy TurboMindエンジンは卓越した推論能力を持ち、さまざ
   <li>Qwen2-VL (2B, 7B, 72B)</li>
   <li>Qwen2.5-VL (3B, 7B, 72B)</li>
   <li>Qwen3-VL (2B - 235B)</li>
-  <li>Qwen3.5</li>
+  <li>Qwen3.5 (27B - 397B)</li>
   <li>DeepSeek-VL (7B)</li>
   <li>DeepSeek-VL2 (3B, 16B, 27B)</li>
   <li>InternVL-Chat (v1.1-v1.5)</li>

README_zh-CN.md

@@ -178,7 +178,7 @@ LMDeploy TurboMind 引擎拥有卓越的推理能力，在各种规模的模型
   <li>Qwen2-VL (2B, 7B, 72B)</li>
   <li>Qwen2.5-VL (3B, 7B, 72B)</li>
   <li>Qwen3-VL (2B - 235B)</li>
-  <li>Qwen3.5</li>
+  <li>Qwen3.5 (27B - 397B)</li>
   <li>DeepSeek-VL (7B)</li>
   <li>DeepSeek-VL2 (3B, 16B, 27B)</li>
   <li>InternVL-Chat (v1.1-v1.5)</li>
@@ -230,7 +230,7 @@ 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=0.12.1
+export LMDEPLOY_VERSION=0.12.2
 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=0.12.1
+export LMDEPLOY_VERSION=0.12.2
 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/quantization/llm_compressor.md

@@ -44,7 +44,7 @@ conda create -n lmdeploy python=3.10 -y
 conda activate lmdeploy
 
 # Install llm-compressor
-pip install llm-compressor
+pip install llmcompressor
 
 # Clone lmdeploy source code and run the quantization example
 git clone https://github.com/InternLM/lmdeploy

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=0.12.1
+export LMDEPLOY_VERSION=0.12.2
 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/quantization/llm_compressor.md

@@ -42,7 +42,7 @@ conda create -n lmdeploy python=3.10 -y
 conda activate lmdeploy
 
 # 安装 llm-compressor
-pip install llm-compressor
+pip install llmcompressor
 
 # 下载 lmdeploy 源码，运行量化用用例
 git clone https://github.com/InternLM/lmdeploy

lmdeploy/pytorch/engine/engine_loop.py

@@ -146,8 +146,7 @@ def _log_resps(outputs: List[InferOutput]):
         if logger.level <= logging.DEBUG:
             session_ids = [out.session_id for out in outputs]
             logger.debug(f'Response sessions: {session_ids}')
-        elif logger.level <= logging.INFO:
-            logger.info(f'Response: num_outputs={len(outputs)}.')
+            logger.debug(f'Response: num_outputs={len(outputs)}.')
 
     def _send_resp(self, out: InferOutput):
         """Send response."""

lmdeploy/serve/core/async_engine.py

@@ -268,7 +268,7 @@ async def safe_run(self, handle, session, **kwargs):
             metrics_processor.increase_api_routed_requests()
             yield generator
         except (Exception, asyncio.CancelledError, GeneratorExit) as e:  # noqa
-            logger.error(f'[safe_run] session {session.session_id} exception caught: {type(e).__name__} {e}')
+            logger.exception(f'[safe_run] session {session.session_id} exception caught: {e}')
             await session.async_abort()
             if self.backend == 'pytorch':
                 await handle.async_end(session.session_id)

lmdeploy/version.py

@@ -1,7 +1,7 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 from typing import Tuple
 
-__version__ = '0.12.1'
+__version__ = '0.12.2'
 short_version = __version__